Your Multimodal Speech Model Says I Have a Face for Radio

# Your Multimodal Speech Model Says I Have a Face for Radio
Source: [https://arxiv.org/html/2605.30472](https://arxiv.org/html/2605.30472)
Maya K\. Nachesa Vlad Niculae Language Technology Lab University of Amsterdam \{[m\.k\.nachesa](https://arxiv.org/html/2605.30472v1/mailto:[email protected]),[v\.niculae](https://arxiv.org/html/2605.30472v1/mailto:[email protected])\}@uva\.nl&Vagrant Gautam Heidelberg Institute for Theoretical Studies [vagrant\.gautam@h\-its\.org](https://arxiv.org/html/2605.30472v1/mailto:[email protected])

###### Abstract

As large neural models have become better at language tasks, researchers are increasingly building multi\- and omnimodal models that handle more modalities of data\. One example is the expansion of speech recognition models to audio\-visual data for noise mitigation and multimodal subtitling\. While performance and bias have been studied extensively in the single\-modality regime, it is unknown how new modalities affect this, even though they produce biases in humans\. We therefore propose the first bias evaluation of multimodal speech recognition, where we create videos pairing different faces with the same audio, and measure changes in speech transcription accuracy\. We find large quality\-of\-service differences acrossmWhisper\-FlamingoandGeminimodels, with drops of up to4\.054\.05word error rate points, across self\-declared gender, ethnicity, and their intersection\. Our findings point to a priority for developers to evaluate, fix, and communicate such limitations, as providing more signals through additional modalities is not necessarily better, and may even lead to biased outcomes\.

Your Multimodal Speech Model Says I Have a Face for Radio

Maya K\. Nachesa Vlad NiculaeLanguage Technology LabUniversity of Amsterdam\{[m\.k\.nachesa](https://arxiv.org/html/2605.30472v1/mailto:[email protected]),[v\.niculae](https://arxiv.org/html/2605.30472v1/mailto:[email protected])\}@uva\.nlVagrant GautamHeidelberg Institutefor Theoretical Studies[vagrant\.gautam@h\-its\.org](https://arxiv.org/html/2605.30472v1/mailto:[email protected])

## 1Introduction

As large neural models improve on single modalities of language data like text or audio, it is becoming increasingly common to incorporate multiple modalities into single “multimodal” or “omnimodal” models, such as images and text\(Radfordet al\.,[2021](https://arxiv.org/html/2605.30472#bib.bib46); Liuet al\.,[2023](https://arxiv.org/html/2605.30472#bib.bib45); Baiet al\.,[2024](https://arxiv.org/html/2605.30472#bib.bib47)\), or video and audio\(Shiet al\.,[2022](https://arxiv.org/html/2605.30472#bib.bib16); Rouditchenkoet al\.,[2024](https://arxiv.org/html/2605.30472#bib.bib11),[2025](https://arxiv.org/html/2605.30472#bib.bib15); Shuet al\.,[2025](https://arxiv.org/html/2605.30472#bib.bib17)\)\. Within audio\-based research, the expansion to multimodality has focused on audio\-visual speech recognition, with applications in noisy environments\(Rouditchenkoet al\.,[2024](https://arxiv.org/html/2605.30472#bib.bib11),[2025](https://arxiv.org/html/2605.30472#bib.bib15)\), automatic video captioning, subtitling\(El Idrissiet al\.,[2025](https://arxiv.org/html/2605.30472#bib.bib41)\), and more\.

Auditory and visual processes are also implicated in human speech perception\(McGurk and MacDonald,[1976](https://arxiv.org/html/2605.30472#bib.bib10)\), where it similarly helps us deal with noisy environments\(Sumby and Pollack,[1954](https://arxiv.org/html/2605.30472#bib.bib32)\)\. However, visual perceptions of the speaker can sometimes worsen our auditory processing of their speech, a phenomenon termedreverse linguistic stereotyping\(Kang and Rubin,[2009](https://arxiv.org/html/2605.30472#bib.bib22)\)\. In other words, nonlinguistic factors such as visually\-perceived speaker ethnicity affect speech perception and processing\(Rubin and Smith,[1990](https://arxiv.org/html/2605.30472#bib.bib20); Rubin,[1992](https://arxiv.org/html/2605.30472#bib.bib25); Zheng and Samuel,[2017](https://arxiv.org/html/2605.30472#bib.bib24); Bhuvanagiriet al\.,[2019](https://arxiv.org/html/2605.30472#bib.bib21); Kutlu,[2023](https://arxiv.org/html/2605.30472#bib.bib12)\)\. No study thus far has examined whether such multimodal raciolinguistic biases also appear in audio\-visual speech recognition systems, despite a long history of study in single\-modality settings in vision\(Buolamwini and Gebru,[2018](https://arxiv.org/html/2605.30472#bib.bib28)\)and in speech\(Koeneckeet al\.,[2020](https://arxiv.org/html/2605.30472#bib.bib13)\)\.

The lack of such studies is largely due to the difficulty of collecting adequate data: Videos must be*audio\-matched*to eliminate confounding factors, as in the matched\-guise setup from sociolinguistics\. We propose a synthetic setup that allows us to evaluate whether the ethnicity and gender of different faces affects audio\-visual speech recognition performance at scale\. We construct a dataset of75,00075,000videos where English audio samples that vary in auditory characteristics \(accent and noise\) are systematically paired with lip\-synced faces that vary in visual characteristics \(ethnicity and gender\)\. Using this dataset, we evaluate audio\-visual speech recognition with two models:mWhisper\-Flamingo medium\(Rouditchenkoet al\.,[2025](https://arxiv.org/html/2605.30472#bib.bib15)\)andGemini\-2\.52\.5\-Flash\(Comaniciet al\.,[2025](https://arxiv.org/html/2605.30472#bib.bib49)\)\.

We show that our synthetic setting is a valid testbed for bias, as our lip\-synced videos help audio\-visual speech recognition \(AVSR\) performance under noisy conditions, just like natural video\. Both with and without noise, AVSR models show single\-axis and intersecting ethnicity and gender biases when transcribing the exact same set of audios with different faces\. Our findings thus provide evidence of reverse linguistic stereotyping in AVSR models\. We hope that our work spurs developers to fix bias in contexts where biases may come from multiple modalities, towards better and fairer multimodal speech recognition\.111Code at:[github\.com/ltl\-uva/MultiModalSpeechBias](https://github.com/ltl-uva/MultiModalSpeechBias)\.

#### Bias statement\.

In response to calls for clearer articulations of bias in language technology\(Blodgettet al\.,[2020](https://arxiv.org/html/2605.30472#bib.bib30); Wanget al\.,[2022](https://arxiv.org/html/2605.30472#bib.bib26)\), we conceptualize bias in our work as differences in quality\-of\-service with audio\-visual speech recognition, based purely on a change in visual cues such as race and gender that should be irrelevant to transcription of the exact same audio\. Our definition of bias is parallel to reverse linguistic stereotyping in humans, and we measure it by testing for statistically significant changes in word error rate \(WER\), which can have detrimental effects on users of speech recognition technologies\(Mengeshaet al\.,[2021](https://arxiv.org/html/2605.30472#bib.bib48); Markl,[2022](https://arxiv.org/html/2605.30472#bib.bib52)\)\.

## 2Related Works

#### Multimodal speech perception in humans\.

The exact same English audio gets different intelligibility ratings from listeners when paired with pictures of White versus South Asian faces\(Kutlu,[2023](https://arxiv.org/html/2605.30472#bib.bib12)\), or Asian faces\(Rubin,[1992](https://arxiv.org/html/2605.30472#bib.bib25)\)\. However, this effect seems to disappear with video\(Zheng and Samuel,[2017](https://arxiv.org/html/2605.30472#bib.bib24)\)\. Notably, these works use a very small sample size \(three unambiguous words, presented on an accent continuum inZheng and Samuel \([2017](https://arxiv.org/html/2605.30472#bib.bib24)\)\), whereas we test at a much larger scale with automated and computational methods\. Our methods are inspired by this literature \(in particular the matched\-guise test setup\), but we evaluate speech recognition systems rather than human listeners, and focus on transcription rather than speaker attitudes as in some of these studies\.

#### Single\-modality bias in vision and speech\.

Prior to our work, quality\-of\-service differentials based on race and gender have been shown in image classification\(Buolamwini and Gebru,[2018](https://arxiv.org/html/2605.30472#bib.bib28)\), image captioning\(Hendrickset al\.,[2018](https://arxiv.org/html/2605.30472#bib.bib29); Wolfe and Caliskan,[2022](https://arxiv.org/html/2605.30472#bib.bib27)\), and English speech recognition\(Tatman,[2017](https://arxiv.org/html/2605.30472#bib.bib14); Koeneckeet al\.,[2020](https://arxiv.org/html/2605.30472#bib.bib13)\)\. In contrast to our work, none of these papers study multi\-modal speech recognition biases\. Additionally, work on bias in speech recognition tends to focus on acoustically\-perceptible differences \(accent, dialect, etc\.\), in contrast to our work, where identical audio is paired with differentvisualinput\.

#### Multi\- and omnimodal models\.

Analyses of multimodal models focus overwhelmingly on vision\-language models that take images and text as input\. For instance,Fuet al\.\([2025](https://arxiv.org/html/2605.30472#bib.bib38)\)show that these models tend to overlook their vision input representations,Kamruzzamanet al\.\([2025](https://arxiv.org/html/2605.30472#bib.bib34)\)analyze how race, gender, and skin tone affect these models’ attribution of emotions,Buiet al\.\([2025](https://arxiv.org/html/2605.30472#bib.bib40)\)evaluate multimodal, multicultural hate speech, andKimet al\.\([2025](https://arxiv.org/html/2605.30472#bib.bib39)\)evaluate models’ cultural stereotypes when visual ethnicity information is perturbed\. Although this last paper’s methodology is similar to ours in terms of systematically perturbing ethnicity features, our work focuses on video and speech modalities, which none of the above consider\. Closest to our work,Daiet al\.\([2024](https://arxiv.org/html/2605.30472#bib.bib33)\)evaluate the robustness of audiovisual speech recognition to dropped frames, while we look at robustness to variance in the visual component of the input\.

## 3Methodology

The dominant signal for speech recognition is the audio\. In order to disentangle the impact of visual biases from audio\-level performance differences in AVSR, we require a controlled setup with rich demographic information\. No such audio\-visual dataset is publicly available\. Therefore, we create a usefully\-close approximation through modifying and combining existing datasets\. The result allows us to compare the performance of AVSR models with varying visuals \(faces of varying ethnicities and genders\) against the*same*audio signal\.

### 3\.1Dataset

To evaluate multimodal speech recognition bias, we create a dataset of videos that systematically combine faces and audio files, corresponding to experiments in the matched\-guise setup with humans\(Kutlu,[2023](https://arxiv.org/html/2605.30472#bib.bib12); Zheng and Samuel,[2017](https://arxiv.org/html/2605.30472#bib.bib24)\)\.

#### Faces\.

For high\-resolution, standardized photographs of racially diverse faces, we use the Chicago Face Database\(Maet al\.,[2015](https://arxiv.org/html/2605.30472#bib.bib36)\)and the India Face Set\(Lakshmiet al\.,[2021](https://arxiv.org/html/2605.30472#bib.bib35)\)\. From these datasets, we select a total of500500faces that are marked to have a neutral expression\. The faces are equally balanced across five ethnicities\. Using their terminology, these are: Asian American, Black, Indian Asian, Latino/a, and White\.222In the rest of the text, we use the labels Asian, Black, Indian, Latinx, and White, for brevity\.Within each ethnicity, the faces we select are equally balanced across Female and Male, the only two gender labels in the datasets\. Ethnicity and gender in these datasets are self\-reported, and we exclude faces of those who chose not to report\. We ensure that each individual’s face is only included once\.

#### Audio\.

We use English audio from the CommonVoice17\.017\.0dataset\(Ardilaet al\.,[2020](https://arxiv.org/html/2605.30472#bib.bib37)\), and select samples corresponding to the following high\-level accent labels: UK, US, and Indian\. As accents in this dataset are self\-identified, each grouping contains a mixed set of accent profiles, resulting in a sample that reflects some of the diversity of these coarse labels\. We describe accent selection in Appendix[A](https://arxiv.org/html/2605.30472#A1)\. Since all audio samples are self\-recorded under diverse recording conditions, audio quality varies widely\. We use a heuristic based on audio ratings from CommonVoice to obtain the top5050audio samples per accent, as outlined in Appendix[B](https://arxiv.org/html/2605.30472#A2)\. As many participants do not indicate gender, we ignore gender labels and focus on quality\. With5050samples each from three accents, we have a total of150150distinct audio files\. As CommonVoice is not designed to collect the same text for different accents or speakers, there are no repeated texts\.

#### Pairing faces and audio\.

All faces are combined with all audios, leading to a total of500500faces×\\times33accents×\\times5050audios==75,00075,000data points\. For each combination, we create an audio\-video file where the video is lip\-synced to the audio withWav2Lip\+\+GAN\(Prajwalet al\.,[2020](https://arxiv.org/html/2605.30472#bib.bib18)\), using the clean audio data as input\. All videos are first downscaled to a height of256256, maintaining the original aspect ratio, to fit the lip\-sync model\. Our use of lip\-synced videos reflects realistic and intended usage of audio\-visual models, in contrast to most sociolinguistic work where still faces are used\. We additionally provide results with videos of static faces in Appendix[G](https://arxiv.org/html/2605.30472#A7), for reference\.

Table 1:Average per\-accent WER scores of AVSR systems compared to audio\-only ASR versions thereof\.mWhisper\-F=mWhisper\-Flamingo medium;Gemini=Gemini\-2\.52\.5\-flash\.As AVSR mostly benefits from visual input in the presence of noise, we also generate noisy versions of the audio\-video files by adding “babble” noise with a Signal\-to\-Noise Ratio \(SNR\) of55dB to the audio track\. We obtain this noise fromRouditchenkoet al\.\([2025](https://arxiv.org/html/2605.30472#bib.bib15)\), which in turn is sampled from the MUSAN dataset\(Snyderet al\.,[2015](https://arxiv.org/html/2605.30472#bib.bib44)\)\.

ModelAccentΔ\\DeltaWER \(Max−\-Min\)EthnicityGenderIntersectionNo noise \(SNR=∞=\\infty\)mWhisper\-FIndian2\.062\.06^\{\\phantom\{\*\}\}\(Indian−\-Asian\)1\.141\.14^\{\\phantom\{\*\}\}\(M−\-F\)4\.05∗4\.05^\{\*\}\(Indian male−\-Asian male\)mWhisper\-FUS0\.720\.72^\{\\phantom\{\*\}\}\(Black−\-Asian\)0\.430\.43^\{\\phantom\{\*\}\}\(M−\-F\)0\.980\.98^\{\\phantom\{\*\}\}\(Black male−\-Latinx female\)mWhisper\-FUK0\.510\.51^\{\\phantom\{\*\}\}\(Indian−\-Asian\)1\.34∗1\.34^\{\*\}\(M−\-F\)2\.27∗2\.27^\{\*\}\(Indian male−\-Latinx female\)GeminiIndian0\.770\.77^\{\\phantom\{\*\}\}\(Indian−\-White\)0\.250\.25^\{\\phantom\{\*\}\}\(F−\-M\)1\.19∗1\.19^\{\*\}\(Indian male−\-White male\)GeminiUS0\.130\.13^\{\\phantom\{\*\}\}\(Indian−\-White\)0\.080\.08^\{\\phantom\{\*\}\}\(M−\-F\)0\.260\.26^\{\\phantom\{\*\}\}\(Asian male−\-Asian female\)GeminiUK0\.490\.49^\{\\phantom\{\*\}\}\(Indian−\-Black\)0\.350\.35^\{\\phantom\{\*\}\}\(M−\-F\)0\.900\.90^\{\\phantom\{\*\}\}\(Indian male−\-Black female\)Babble noise \(SNR=5=5\)mWhisper\-FIndian1\.011\.01^\{\\phantom\{\*\}\}\(Indian−\-Asian\)0\.100\.10^\{\\phantom\{\*\}\}\(F−\-M\)1\.711\.71^\{\\phantom\{\*\}\}\(Indian male−\-Asian male\)mWhisper\-FUS1\.75∗1\.75^\{\*\}\(Indian−\-Asian\)1\.45∗1\.45^\{\*\}\(M−\-F\)3\.95∗3\.95^\{\*\}\(Indian male−\-Asian female\)mWhisper\-FUK0\.910\.91^\{\\phantom\{\*\}\}\(Black−\-White\)0\.470\.47^\{\\phantom\{\*\}\}\(F−\-M\)2\.84∗2\.84^\{\*\}\(Indian male−\-Latinx male\)GeminiIndian1\.49∗1\.49^\{\*\}\(Asian−\-White\)0\.510\.51^\{\\phantom\{\*\}\}\(M−\-F\)2\.73∗2\.73^\{\*\}\(Asian male−\-White male\)GeminiUS0\.530\.53^\{\\phantom\{\*\}\}\(Black−\-White\)0\.200\.20^\{\\phantom\{\*\}\}\(F−\-M\)0\.95∗0\.95^\{\*\}\(Latinx female−\-White male\)GeminiUK1\.031\.03^\{\\phantom\{\*\}\}\(Black−\-White\)0\.430\.43^\{\\phantom\{\*\}\}\(M−\-F\)1\.62∗1\.62^\{\*\}\(Black male−\-White female\)Table 2:Largest AVSR quality\-of\-service differences between faces, across ethnicity, gender, and their intersection\. Asterisk \(\*\) denotes statistical significance \(p<0\.005p<0\.005\) according to a permutation test \(Section[3\.2](https://arxiv.org/html/2605.30472#S3.SS2)\)\.mWhisper\-F=mWhisper\-Flamingo medium;Gemini=Gemini\-2\.52\.5\-flash\. M = Male; F = Female\.

### 3\.2Experimental Setup

#### Models\.

We ran our experiments usingmWhisper\-Flamingo medium333We ran preliminary experiments withmWhisper\-Flamingo smallandWhisper\-Flamingo, but exclude those as they perform much worse\.\(Rouditchenkoet al\.,[2025](https://arxiv.org/html/2605.30472#bib.bib15)\)andGemini\-2\.52\.5\-Flash\(Comaniciet al\.,[2025](https://arxiv.org/html/2605.30472#bib.bib49)\)\. As input,mWhisper\-Flamingotakes audio and greyscaled video, cropped to the mouth region, separately\. As forGemini, the full video is encoded in Base64\. We show prompts forGeminiin Appendix[D](https://arxiv.org/html/2605.30472#A4)\. We also report results with an automatic speech recognition \(ASR\) baseline obtained by turning off the video input, which both models support\.

#### Metrics\.

We assess model performance with WER: The corpus\-level average number of errors weighted by document length\. Implementation notes are provided in Appendix[E](https://arxiv.org/html/2605.30472#A5)\. We also compute WER standard deviations as a weighted average of the per\-document difference to the mean, and estimate standard errors of the mean WER using the normal assumption\.

For statistical testing of significant pairwise quality\-of\-service differences \(Table[2](https://arxiv.org/html/2605.30472#S3.T2)\), we apply10,00010,000iterations of a one\-sided permutation test, stratified over audio files\. To correct for multiple comparisons within each row, we apply the*max\-T*method\(Westfall and Young,[1993](https://arxiv.org/html/2605.30472#bib.bib54)\)\. To correct for the number of rows, we use the Bonferroni method\.

## 4Main Findings

Table[1](https://arxiv.org/html/2605.30472#S3.T1)provides an overview of WERs on average, compared to an ASR\-only \(i\.e\., no visual input\) baseline\. See Appendix[C](https://arxiv.org/html/2605.30472#A3)for a full breakdown by gender and ethnicity conditions\. Overall,Geminimodels perform better thanmWhisper\-Flamingomodels in all settings \(despite some hallucinations and deviations from instructions \- see Appendix[F](https://arxiv.org/html/2605.30472#A6)\)\. We caution, however, thatGemini’s better performance could be due to train\-test contamination\. US accents are transcribed better than UK accents, which in turn are transcribed better than Indian accents\. These performance differences could also come from differences in audio quality, however, they pattern similarly to previously\-studied accent biases in ASR models\(Chanet al\.,[2022](https://arxiv.org/html/2605.30472#bib.bib51); DiChristofanoet al\.,[2023](https://arxiv.org/html/2605.30472#bib.bib53)\)\.

#### Lip\-synced input is useful for AVSR under noise\.

In the absence of noise, visual input degrades recognition performance\. However, when we add noise at an SNR of55dB, compared to ASR alone,mWhisper\-Flamingoimproves for UK accents, andGeminiimproves in all settings\. This aligns with the motivation and results inmWhisper\-Flamingo\(Rouditchenkoet al\.,[2025](https://arxiv.org/html/2605.30472#bib.bib15)\), and suggests that our synthetic data setup resembles realistic conditions\. Audio signals are often enough for ASR, as they are in some sense captured more faithfully than video \(where mouths may be badly cropped or undetected, or faces may be off\-camera\)\. Nevertheless, the fact that video sometimesworsensrather than maintains performance under no noise points to the infancy of these models\.

#### Models show ethnicity and gender biases when transcribing the same audio with different faces\.

As Table[2](https://arxiv.org/html/2605.30472#S3.T2)shows, there are several statistically significant quality\-of\-service differences in transcribing the exact same set of audios with different groupings of faces, across both models and all accent classes\. While some single\-axis ethnicity and gender differences may not be significant, they hideintersectingbiases as in other settings in both vision\(Buolamwini and Gebru,[2018](https://arxiv.org/html/2605.30472#bib.bib28)\)and language\(Rodríguezet al\.,[2025](https://arxiv.org/html/2605.30472#bib.bib50)\): Indian male faces consistently worsenmWhisper\-Flamingo’s transcription, and White male faces consistently get the best WERs withGemini\. In fact, results even seem to worsen under noise, where we have seen that models rely more on their visual input as well\. These results provide evidence of the reverse linguistic stereotyping effect in models, and point to an important priority for model developers to fix\.

## 5Conclusion

We contribute a framework to study biases in audiovisual speech recognition by creating videos that present the same audio with lip\-synced faces that vary along the dimensions of ethnicity and gender\. WERs withmWhisper\-FlamingoandGemini\-2\.52\.5\-flashconfirm that our synthetic setup, while inferior to real videos of people speaking, simulates it well enough, as it improves transcription over audio\-only ASR under noise\. We then show that models show single\-axis and intersecting ethnicity and gender biases when transcribing the same audio with different faces\. Our results provide evidence of reverse linguistic stereotyping in AVSR models, and suggest that synthetic data with lip\-sync might be a useful avenue to mitigate these quality\-of\-service differences\. Fixing such biases that emerge from the combination of multiple modalities is an important priority for the future of multi\- and omnimodal language technology and research\.

## Limitations

The primary limitation of this work is that we evaluate with stand\-ins for real video: Lip\-synced videos in the main text, and videos with static faces in Appendix[G](https://arxiv.org/html/2605.30472#A7)\. Second, we work with a limited set of accents and faces, as well as only in English, while results are sure to differ in other languages and with a broader variety of facial and dialectal differences\. Finally, we use self\-declared ethnicity, gender, and accent labels, which is good for participant autonomy and dignity, but we note thatperceptionsof people may differ from identity, and this is likely to play a larger role in bias in computational systems\.

## Ethics Statement

Ethnicity and gender are multi\-faceted aspects of identity, and our operationalization choices affect the conclusions we can draw\(Steidl and Werum,[2019](https://arxiv.org/html/2605.30472#bib.bib42)\)\. Ethnicity, gender, and accent are all self\-declared in the data we use\. Although this supports participant autonomy and dignity, perceptions and behaviour \(from both humans and machines\) may differ, which can cause harm to individuals\. Our results show quality\-of\-service differentials in AVSR that replicate structural power differentials in society and are an example of algorithmic oppression, with harms to users of these technologies with certain faces\. We use all datasets in compliance with their terms of use and licensing restrictions, i\.e\., we do not identify the owners of the faces or voices, we use the face data only for non\-commercial scientific research, and we use CommonVoice for evaluating speech recognition models\.

## Acknowledgments

We thank Aashutosh Ganesh and Annika Kniele for their valuable feedback\. We are grateful to RTL Netherlands for compute resources\. This publication is part of the project*ROBUST: Trustworthy AI\-based Systems for Sustainable Growth*with project number KICH3\.LTP\.20\.006, which is \(partly\) financed by the Dutch Research Council \(NWO\), RTL, and the Dutch Ministry of Economic Affairs and Climate Policy \(EZK\) under the program LTP KIC 2020\-2023\. Vagrant Gautam’s work is funded by the Klaus Tschira Foundation, Heidelberg, Germany\. Vlad Niculae is supported by the Dutch Research Council \(NWO\) via VI\.Veni\.212\.228\.

## References

- R\. Ardila, M\. Branson, K\. Davis, M\. Kohler, J\. Meyer, M\. Henretty, R\. Morais, L\. Saunders, F\. Tyers, and G\. Weber \(2020\)Common voice: a massively\-multilingual speech corpus\.Marseille, France,pp\. 4218–4222\(eng\)\.External Links:[Link](https://aclanthology.org/2020.lrec-1.520/),ISBN 979\-10\-95546\-34\-4Cited by:[§3\.1](https://arxiv.org/html/2605.30472#S3.SS1.SSS0.Px2.p1.4)\.
- Qwen\-VL: a versatile vision\-language model for understanding, localization, text reading, and beyond\.External Links:[Link](https://openreview.net/forum?id=qrGjFJVl3m)Cited by:[§1](https://arxiv.org/html/2605.30472#S1.p1.1)\.
- D\. Bhuvanagiri, A\. Grahlherr, P\. Beardsell, J\. Chittoor, and D\. Rubin \(2019\)The role of race in the stereotyping of a speaker’s accent as native or non\-native\.Journal of Emerging Investigators\.External Links:[Link](https://emerginginvestigators.org/articles/18-002),[Document](https://dx.doi.org/10.59720/18-002)Cited by:[§1](https://arxiv.org/html/2605.30472#S1.p2.1)\.
- S\. L\. Blodgett, S\. Barocas, H\. Daumé III, and H\. Wallach \(2020\)Language \(technology\) is power: a critical survey of “bias” in NLP\.Online,pp\. 5454–5476\.External Links:[Link](https://aclanthology.org/2020.acl-main.485/),[Document](https://dx.doi.org/10.18653/v1/2020.acl-main.485)Cited by:[§1](https://arxiv.org/html/2605.30472#S1.SS0.SSS0.Px1.p1.1)\.
- M\. D\. Bui, K\. V\. D\. Wense, and A\. Lauscher \(2025\)Multi3Hate: multimodal, multilingual, and multicultural hate speech detection with vision–language models\.Albuquerque, New Mexico,pp\. 9714–9731\.External Links:[Link](https://aclanthology.org/2025.naacl-long.490/),[Document](https://dx.doi.org/10.18653/v1/2025.naacl-long.490),ISBN 979\-8\-89176\-189\-6Cited by:[§2](https://arxiv.org/html/2605.30472#S2.SS0.SSS0.Px3.p1.1)\.
- J\. Buolamwini and T\. Gebru \(2018\)Gender shades: intersectional accuracy disparities in commercial gender classification\.InProceedings of the 1st Conference on Fairness, Accountability and TransparencyComputer Vision – ECCV 2018Proceedings of the 58th Annual Meeting of the Association for Computational LinguisticsInternational conference on machine learningProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition \(CVPR\)Findings of the Association for Computational Linguistics: EMNLP 2025Proceedings of the Twelfth Language Resources and Evaluation ConferenceSecond Conference on Language ModelingProceedings of the 3rd Workshop on Cross\-Cultural Considerations in NLP \(C3NLP 2025\)Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies \(Volume 1: Long Papers\)International Conference on Advances in Communication Technology and Computer EngineeringProceedings of the 2019 conference of the North American chapter of the association for computational linguistics \(Demonstrations\)Advances in Neural Information Processing SystemsProceedings of the 38th International Conference on Machine LearningProceedings of the 6th Workshop on Gender Bias in Natural Language Processing \(GeBNLP\)Interspeech 2022Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency,S\. A\. Friedler, C\. Wilson, V\. Ferrari, M\. Hebert, C\. Sminchisescu, Y\. Weiss, D\. Jurafsky, J\. Chai, N\. Schluter, J\. Tetreault, C\. Christodoulopoulos, T\. Chakraborty, C\. Rose, V\. Peng, N\. Calzolari, F\. Béchet, P\. Blache, K\. Choukri, C\. Cieri, T\. Declerck, S\. Goggi, H\. Isahara, B\. Maegaard, J\. Mariani, H\. Mazo, A\. Moreno, J\. Odijk, S\. Piperidis, V\. Prabhakaran, S\. Dev, L\. Benotti, D\. Hershcovich, Y\. Cao, L\. Zhou, L\. Cabello, I\. Adebara, L\. Chiruzzo, A\. Ritter, L\. Wang, A\. Oh, T\. Naumann, A\. Globerson, K\. Saenko, M\. Hardt, S\. Levine, M\. Meila, T\. Zhang, A\. Faleńska, C\. Basta, M\. Costa\-jussà, K\. Stańczak, and D\. Nozza \(Eds\.\),Proceedings of Machine Learning ResearchProceedings of Machine Learning ResearchFAccT ’22, Vol\.8136139,pp\. 77–91\.External Links:[Link](https://proceedings.mlr.press/v81/buolamwini18a.html)Cited by:[§1](https://arxiv.org/html/2605.30472#S1.p2.1),[§2](https://arxiv.org/html/2605.30472#S2.SS0.SSS0.Px2.p1.1),[§4](https://arxiv.org/html/2605.30472#S4.SS0.SSS0.Px2.p1.1)\.
- M\. P\. Y\. Chan, J\. Choe, A\. Li, Y\. Chen, X\. Gao, and N\. Holliday \(2022\)Training and typological bias in ASR performance for world Englishes\.pp\. 1273–1277\.External Links:[Document](https://dx.doi.org/10.21437/Interspeech.2022-10869),ISSN 2958\-1796Cited by:[§4](https://arxiv.org/html/2605.30472#S4.p1.1)\.
- G\. Comanici, E\. Bieber, M\. Schaekermann, I\. Pasupat, N\. Sachdeva, I\. Dhillon, M\. Blistein, O\. Ram, D\. Zhang, E\. Rosen, L\. Marris, S\. Petulla, C\. Gaffney, A\. Aharoni, N\. Lintz, T\. C\. Pais, H\. Jacobsson, I\. Szpektor, N\. Jiang, K\. Haridasan, A\. Omran, N\. Saunshi, D\. Bahri, G\. Mishra, E\. Chu, T\. Boyd, B\. Hekman, A\. Parisi, C\. Zhang, K\. Kawintiranon, T\. Bedrax\-Weiss, O\. Wang, Y\. Xu, O\. Purkiss, U\. Mendlovic, I\. Deutel, N\. Nguyen, A\. Langley, F\. Korn, L\. Rossazza, A\. Ramé, S\. Waghmare, H\. Miller, N\. Byrd, A\. Sheshan, R\. Hadsell, S\. Bhardwaj, P\. Janus, T\. Rissa, D\. Horgan, A\. Abdagic, L\. Belenki, J\. Allingham, A\. Singh, T\. Guidroz, S\. Srinivasan, H\. Schmit, K\. Chiafullo, A\. Elisseeff, N\. Jha, P\. Kolhar, L\. Berrada, F\. Ding, X\. Si, S\. B\. Mallick, F\. Och, S\. Erell, E\. Ni, T\. Latkar, S\. Yang, P\. Sirkovic, Z\. Feng, R\. Leland, R\. Hornung, G\. Wu, C\. Blundell, H\. Alvari, P\. Huang, C\. Yip, S\. Deur, L\. Liu, G\. Surita, P\. Duque, D\. Damen, J\. Jia, A\. Guez, M\. Mircea, A\. Sinha, A\. Magni, P\. Stradomski, T\. Marian, V\. Galić, W\. Chen, H\. Husain, A\. Singhal, D\. Grewe, F\. Aubet, S\. Song, L\. Blanco, L\. Rechis, L\. Ho, R\. Munoz, K\. Zheng, J\. Hamrick, K\. Mather, H\. Taitelbaum, E\. Rutherford, Y\. Lei, K\. Chen, A\. Shukla, E\. Moreira, E\. Doi, B\. Isik, N\. Shabat, D\. Rogozińska, K\. Kolipaka, J\. Chang, E\. Vušak, S\. Venkatachary, S\. Noghabi, T\. Bharti, Y\. Jun, A\. Zaks, S\. Green, J\. Challagundla, W\. Wong, M\. Mohammad, D\. Hirsch, Y\. Cheng, I\. Naim, L\. Proleev, D\. Vincent, A\. Singh, M\. Krikun, D\. Krishnan, Z\. Ghahramani, A\. Atias, R\. Aggarwal, C\. Kirov, D\. Vytiniotis, C\. Koh, A\. Chronopoulou, P\. Dogra, V\. Ion, G\. Tyen, J\. Lee, F\. Weissenberger, T\. Strohman, A\. Balakrishna, J\. Rae, M\. Velic, R\. de Liedekerke, O\. Elyada, W\. Yuan, C\. Liu, L\. Shani, S\. Kishchenko, B\. Alessio, Y\. Li, R\. Song, S\. Kwei, O\. Jankowski, A\. Pappu, Y\. Namiki, Y\. Ma, N\. Tripuraneni, C\. Cherry, M\. Ikonomidis, Y\. Ling, C\. Ji, B\. Westberg, A\. Wright, D\. Yu, D\. Parkinson, S\. Ramaswamy, J\. Connor, S\. H\. Yeganeh, S\. Grover, G\. Kenwright, L\. Litchev, C\. Apps, A\. Tomala, F\. Halim, A\. Castro\-Ros, Z\. Li, A\. Boral, P\. Sho, M\. Yarom, E\. Malmi, D\. Klinghoffer, R\. Lin, A\. Ansell, P\. K\. S, S\. Zhao, S\. Zuo, A\. Santoro, H\. Cheng, S\. Demmessie, Y\. Liu, N\. Brichtova, A\. Culp, N\. Braun, D\. Graur, W\. Ng, N\. Mehta, A\. Phillips, P\. Sundberg, V\. Godbole, F\. Liu, Y\. Katariya, D\. Rim, M\. Seyedhosseini, S\. Ammirati, J\. Valfridsson, M\. Malihi, T\. Knight, A\. Toor, T\. Lampe, A\. Ittycheriah, L\. Chiang, C\. Yeung, A\. Fréchette, J\. Rao, H\. Wang, H\. Srivastava, R\. Zhang, R\. Rhodes, A\. Brand, D\. Weesner, I\. Figotin, F\. Gimeno, R\. Fellinger, P\. Marcenac, J\. Leal, E\. Marcus, V\. Cotruta, R\. Cabrera, S\. Luo, D\. Garrette, V\. Axelrod, S\. Baltateanu, D\. Barker, D\. Chen, H\. Toma, B\. Ingram, J\. Riesa, C\. Kulkarni, Y\. Zhang, H\. Liu, C\. Wang, M\. Polacek, W\. Wu, K\. Hui, A\. N\. Reyes, Y\. Su, M\. Barnes, I\. Malhi, A\. Siddiqui, Q\. Feng, M\. Damaschin, D\. Pighin, A\. Steiner, S\. Yang, R\. S\. Boppana, S\. Ivanov, A\. Kandoor, A\. Shah, A\. Mujika, D\. Huang, C\. A\. Choquette\-Choo, M\. Patel, T\. Yu, T\. Creswell, Jerry, Liu, C\. Barros, Y\. Razeghi, A\. Roy, P\. Culliton, B\. Xiong, J\. Pan, T\. Strohmann, T\. Powell, B\. Seal, D\. DeCarlo, P\. Shyam, K\. Katircioglu, X\. Wang, C\. Hardin, I\. Odisho, J\. Broder, O\. Chang, A\. Nair, A\. Shtefan, M\. O’Brien, M\. Agarwal, S\. Potluri, S\. Goyal, A\. Jhindal, S\. Thakur, Y\. Stuken, J\. Lyon, K\. Toutanova, F\. Feng, A\. Wu, B\. Horn, A\. Wang, A\. Cullum, G\. Taubman, D\. Shrivastava, C\. Shi, H\. Tomlinson, R\. Patel, T\. Tu, A\. M\. Oflazer, F\. Pongetti, M\. Yang, A\. A\. Taïga, V\. Perot, N\. W\. Pierse, F\. Han, Y\. Drori, I\. Iturrate, A\. Chakrabarti, L\. Yeung, D\. Dopson, Y\. Chen, A\. Kulshreshtha, T\. Guo, P\. Pham, T\. Schuster, J\. Chen, A\. Polozov, J\. Xing, H\. Zhou, P\. Kacham, D\. Kukliansky, A\. Miech, S\. Yaroshenko, E\. Chi, S\. Douglas, H\. Fei, M\. Blondel, P\. Myla, L\. Madmoni, X\. Wu, D\. Keysers, K\. Kjems, I\. Albuquerque, L\. Yu, J\. D’sa, M\. Plantan, V\. Ionescu, J\. S\. Elias, A\. Gupta, M\. R\. Vuyyuru, F\. Alcober, T\. Zhou, K\. Ji, F\. Hartmann, S\. Puttagunta, H\. Song, E\. Amid, A\. Stefanoiu, A\. Lee, P\. Pucciarelli, E\. Wang, A\. Raul, S\. Petrov, I\. Tian, V\. Anklin, N\. Nti, V\. Gomes, M\. Schumacher, G\. Vesom, A\. Panagopoulos, K\. Bousmalis, D\. Andor, J\. Jacob, Y\. Zhang, B\. Rosgen, M\. Kecman, M\. Tung, A\. Belias, N\. Goodman, P\. Covington, B\. Wieder, N\. Saxena, E\. Davoodi, M\. Huang, S\. Maddineni, V\. Roulet, F\. Campbell\-Ajala, P\. G\. Sessa, Xintian, Wu, G\. Lai, P\. Collins, A\. Haig, V\. Sakenas, X\. Xu, M\. Giustina, L\. E\. Shafey, P\. Charoenpanit, S\. Garg, J\. Ainslie, B\. Severson, M\. G\. Arenas, S\. Pathak, S\. Rajayogam, J\. Feng, M\. Bakker, S\. Li, N\. Wichers, J\. Rogers, X\. Geng, Y\. Li, R\. Jagerman, C\. Jia, N\. Olmert, D\. Sharon, M\. Mauger, S\. Mariserla, H\. Ma, M\. Mohabey, K\. Kim, A\. Andreev, S\. Pollom, J\. Love, V\. Jain, P\. Agrawal, Y\. Schroecker, A\. Fortin, M\. Warmuth, J\. Liu, A\. Leach, I\. Blok, G\. P\. Girirajan, R\. Aharoni, B\. Uria, A\. Sozanschi, D\. Goldberg, L\. Ionita, M\. T\. Ribeiro, M\. Zlocha, V\. Birodkar, S\. Lachgar, L\. Yuan, H\. Choudhury, M\. Ginsberg, F\. Zheng, G\. Dibb, E\. Graves, S\. Lokhande, G\. Rasskin, G\. Muraru, C\. Quick, S\. Tata, P\. Sermanet, A\. Chawla, I\. Karo, Y\. Wang, S\. Zhang, O\. Keller, A\. Dragan, G\. Su, I\. Chou, X\. Liu, Y\. Tao, S\. Prabhakara, M\. Wilson, R\. Liu, S\. Wang, G\. Evans, D\. Du, A\. Castaño, G\. Prasad, M\. E\. Mahdy, S\. Gerlach, M\. Reid, J\. Kahn, A\. Zait, T\. S\. Pillai, T\. Ulrich, G\. Wang, J\. Wassenberg, E\. Farkash, K\. Yalasangi, C\. Wang, M\. Bauza, S\. Bucher, T\. Liu, J\. Yan, G\. Leung, V\. Sindhwani, P\. Barnes, A\. Singh, I\. Jurin, J\. Chang, N\. K\. Bhumihar, S\. Eiger, G\. Citovsky, B\. Withbroe, Z\. Li, S\. Xue, N\. D\. Santo, G\. Stoyanov, Y\. Raimond, S\. Zheng, Y\. Gao, V\. Listík, S\. Kwasiborski, R\. Saputro, A\. Ozturel, G\. Mallya, K\. Majmundar, R\. West, P\. Caron, J\. Wei, L\. Castrejon, S\. Vikram, D\. Ramachandran, N\. Dhawan, J\. Park, S\. Smoot, G\. van den Driessche, Y\. Blau, C\. Malik, W\. Liang, R\. Hirsch, C\. N\. dos Santos, E\. Weinstein, A\. van den Oord, S\. Lall, N\. FitzGerald, Z\. Jiang, X\. Yang, D\. Webster, A\. Elqursh, A\. Pope, G\. Rotival, D\. Raposo, W\. Zhu, J\. Dean, S\. Alabed, D\. Tran, A\. Gupta, Z\. Gleicher, J\. Austin, E\. Rosseel, M\. Umekar, D\. Das, Y\. Sun, K\. Chen, K\. Misiunas, X\. Zhou, Y\. Di, A\. Loo, J\. Newlan, B\. Li, V\. Ramasesh, Y\. Xu, A\. Chen, S\. Gandhe, R\. Soricut, N\. Gupta, S\. Hu, S\. El\-Sayed, X\. Garcia, I\. Brusilovsky, P\. Chen, A\. Bolt, L\. Huang, A\. Gurney, Z\. Zhang, A\. Pritzel, J\. Wilkiewicz, B\. Seybold, B\. K\. Shamanna, F\. Fischer, J\. Dean, K\. Gill, R\. Mcilroy, A\. Bhowmick, J\. Selier, A\. Yang, D\. Cheng, V\. Magay, J\. Tan, D\. Varma, C\. Walder, T\. Kocisky, R\. Nakashima, P\. Natsev, M\. Kwong, I\. Gog, C\. Zhang, S\. Dieleman, T\. Jimma, A\. Ryabtsev, S\. Brahma, D\. Steiner, D\. Du, A\. Žužul, M\. Žanić, M\. Raghavachari, W\. Gierke, Z\. Zheng, D\. Petrova, Y\. Dauphin, Y\. Liu, I\. Kessler, S\. Hand, C\. Duvarney, S\. Kim, H\. Lee, L\. Hussenot, J\. Hui, J\. Smith, D\. Jain, J\. Xia, G\. S\. Tomar, K\. Amiri, D\. Phan, F\. Fuchs, T\. Weyand, N\. Tomasev, A\. Cordell, X\. Liu, J\. Mallinson, P\. Joshi, A\. Crawford, A\. Suggala, S\. Chien, N\. Fernando, M\. Sanchez\-Vargas, D\. Williams, P\. Crone, X\. Luo, I\. Karpov, J\. Shan, T\. Thurk, R\. Strudel, P\. Voigtlaender, P\. Patil, T\. Dozat, A\. Khodaei, S\. Singla, P\. Ambroszczyk, Q\. Wu, Y\. Chang, B\. Roark, C\. Hegde, T\. Ding, A\. Filos, Z\. Wu, A\. S\. Pinto, S\. Liu, S\. Khanna, A\. Pandey, S\. Mcloughlin, Q\. Li, S\. Haves, A\. Zhou, E\. Buchatskaya, I\. Leal, P\. de Boursac, N\. Akazawa, N\. Anderson, T\. Chen, K\. Somandepalli, C\. Liang, S\. Goenka, S\. Winkler, A\. Grushetsky, Y\. Ding, J\. Smith, F\. Ye, J\. Pont\-Tuset, E\. Li, R\. Li, T\. Golany, D\. Wegner, T\. Jiang, O\. Barak, Y\. Shangguan, E\. Vértes, R\. Wong, J\. Bornschein, A\. Tudor, M\. Bevilacqua, T\. Schaul, A\. S\. Rawat, Y\. Zhao, K\. Axiotis, L\. Meng, C\. McLean, J\. Lai, J\. Beattie, N\. Kushman, Y\. Liu, B\. Kutzman, F\. Lang, J\. Ye, P\. Netrapalli, P\. Mishra, M\. Khan, M\. Goel, R\. Willoughby, D\. Tian, H\. Zhuang, J\. Chen, Z\. Tsai, T\. Kementsietsidis, A\. Khare, J\. Keeling, K\. Xu, N\. Waters, F\. Altché, A\. Popat, B\. Mittal, D\. Saxton, D\. E\. Badawy, M\. Mathieu, Z\. Zheng, H\. Zhou, N\. Ranka, R\. Shin, Q\. Duan, T\. Salimans, I\. Mihailescu, U\. Shaham, M\. Chang, Y\. Assael, N\. Dikkala, M\. Izzard, V\. Cohen\-Addad, C\. Graves, V\. Feinberg, G\. Chung, D\. Strouse, D\. Karmon, S\. Sharifzadeh, Z\. Ashwood, K\. Pham, J\. Blanton, A\. Vasiloff, J\. Barber, M\. Geller, A\. Zhou, F\. Zubach, T\. Huang, L\. Zhang, H\. Gupta, M\. Young, J\. Proskurnia, R\. Votel, V\. Gabeur, G\. Barcik, A\. Tripathi, H\. Yu, G\. Yan, B\. Changpinyo, F\. Pavetić, A\. Coyle, Y\. Fujii, J\. G\. Mendez, T\. Zhou, H\. Rajamani, B\. Hechtman, E\. Cao, D\. Juan, Y\. Tan, V\. Dalibard, Y\. Du, N\. Clay, K\. Yao, W\. Jia, D\. Vijaykumar, Y\. Zhou, X\. Bai, W\. Hung, S\. Pecht, G\. Todorov, N\. Khadke, P\. Gupta, P\. Lahoti, A\. Autef, K\. Duddu, J\. Lee\-Thorp, A\. Bykovsky, T\. Misiunas, S\. Flennerhag, S\. Thangaraj, J\. McGiffin, Z\. Nado, M\. Kunesch, A\. Noever, A\. Hertz, M\. Liang, V\. Stone, E\. Palmer, S\. Daruki, A\. Pramanik, S\. Põder, A\. Kyker, M\. Khan, E\. Sluzhaev, M\. Ritter, A\. Ruderman, W\. Zhou, C\. Nagpal, K\. Vodrahalli, G\. Necula, P\. Barham, E\. Pavlick, J\. Hartford, I\. Shafran, L\. Zhao, M\. Mikuła, T\. Eccles, H\. Shimokawa, K\. Garg, L\. Vilnis, H\. Chen, I\. Shumailov, K\. Lee, A\. Abdelhamed, M\. Xie, V\. Cohen, E\. Hlavnova, D\. Malkin, C\. Sitawarin, J\. Lottes, P\. Coquinot, T\. Yu, S\. Kumar, J\. Zhang, A\. Mahendru, Z\. Ahmed, J\. Martens, T\. Chen, A\. Boag, D\. Peng, C\. Devin, A\. Klimovskiy, M\. Phuong, D\. Vainstein, J\. Xie, B\. Ramabhadran, N\. Howard, X\. Yu, G\. Goswami, J\. Cui, S\. Shleifer, M\. Pinto, C\. Yeh, M\. Yang, S\. Javanmardi, D\. Ethier, C\. Lee, J\. Orbay, S\. Kotecha, C\. Bromberg, P\. Shaw, J\. Thornton, A\. G\. Rosenthal, S\. Gu, M\. Thomas, I\. Gemp, A\. Ayyar, A\. Ushio, A\. Selvan, J\. Wee, C\. Liu, M\. Majzoubi, W\. Yu, J\. Abernethy, T\. Liechty, R\. Pan, H\. Nguyen, Qiong, Hu, S\. Perrin, A\. Arora, E\. Pitler, W\. Wang, K\. Shivakumar, F\. Prost, B\. Limonchik, J\. Wang, Y\. Gao, T\. Cour, S\. Buch, H\. Gui, M\. Ivanova, P\. Neubeck, K\. Chan, L\. Kim, H\. Chen, N\. Goyal, D\. Chung, L\. Liu, Y\. Su, A\. Petrushkina, J\. Shen, A\. Joulin, Y\. Xu, S\. X\. Lin, Y\. Kulizhskaya, C\. Chelba, S\. Vasudevan, E\. Collins, V\. Bashlovkina, T\. Lu, D\. Fritz, J\. Park, Y\. Zhou, C\. Su, R\. Tanburn, M\. Sushkov, M\. Rasquinha, J\. Li, J\. Prendki, Y\. Li, P\. LV, S\. Sharma, H\. Fitoussi, H\. Huang, A\. Dai, P\. Dao, M\. Burrows, H\. Prior, D\. Qin, G\. Pundak, L\. L\. Sjoesund, A\. Khurshudov, Z\. Zhu, A\. Webson, E\. Kemp, T\. Tan, S\. Agrawal, S\. Sargsyan, L\. Cheng, J\. Stephan, T\. Kwiatkowski, D\. Reid, A\. Byravan, A\. H\. Michaely, N\. Heess, L\. Zhou, S\. Goenka, V\. Carpenter, A\. Levskaya, B\. Wang, R\. Roberts, R\. Leblond, S\. Chikkerur, S\. Ginzburg, M\. Chang, R\. Riachi, Chuqiao, Xu, Z\. Borsos, M\. Pliskin, J\. Pawar, M\. Lustman, H\. Kirkwood, A\. Anand, A\. Chaudhary, N\. Kalb, K\. Milan, S\. Augenstein, A\. Goldie, L\. Prince, K\. Raman, Y\. Sun, V\. Xia, A\. Cohen, Z\. Huo, J\. Camp, S\. Ellis, L\. Zilka, D\. V\. Torres, L\. Patel, S\. Arora, B\. Chan, J\. Adler, K\. Ayoub, J\. Liang, F\. Jamil, J\. Jiang, S\. Baumgartner, H\. Sun, Y\. Karov, Y\. Akulov, H\. Zheng, I\. Cai, C\. Fantacci, J\. Rubin, A\. R\. Acha, M\. Wang, N\. D’Souza, R\. Sathyanarayana, S\. Dai, S\. Rowe, A\. Simanovsky, O\. Goldman, Y\. Kuang, X\. Pan, A\. Rosenberg, T\. Rojas\-Esponda, P\. Dutta, A\. Zeng, I\. Jurenka, G\. Farquhar, Y\. Bansal, S\. Iqbal, B\. Roelofs, G\. Joung, P\. Beak, C\. Ryu, R\. Poplin, Y\. Wu, J\. Alayrac, S\. Buthpitiya, O\. Ronneberger, C\. Habtegebriel, W\. Li, P\. Cavallaro, A\. Wei, G\. Bensky, T\. Denk, H\. Ganapathy, J\. Stanway, P\. Joshi, F\. Bertolini, J\. Lo, O\. Ma, Z\. Charles, G\. Sampemane, H\. Sahni, X\. Chen, H\. Askham, D\. Gaddy, P\. Young, J\. Tan, M\. Eyal, A\. Bražinskas, L\. Zhong, Z\. Wu, M\. Epstein, K\. Bailey, A\. Hard, K\. Lee, S\. Goldshtein, A\. Ruiz, M\. Badawi, M\. Lochbrunner, J\. Kearns, A\. Brown, F\. Pardo, T\. Weber, H\. Yang, P\. Jiang, B\. Akin, Z\. Fu, M\. Wainwright, C\. Zou, M\. Gaba, P\. Manzagol, W\. Kan, Y\. Song, K\. Zainullina, R\. Lin, J\. Ko, S\. Deshmukh, A\. Jindal, J\. Svensson, D\. Tyam, H\. Zhao, C\. Kaeser\-Chen, S\. Baird, P\. Moradi, J\. Hall, Q\. Guo, V\. Tsang, B\. Liang, F\. Pereira, S\. Ganesh, I\. Korotkov, J\. Adamek, S\. Thiagarajan, V\. Tran, C\. Chen, C\. Tar, S\. Jain, I\. Dasgupta, T\. Bilal, D\. Reitter, K\. Zhao, G\. Vezzani, Y\. Gehman, P\. Mehta, L\. Beltrone, X\. Dotiwalla, S\. Guadarrama, Z\. Abbas, S\. Karp, P\. Georgiev, C\. Ferng, M\. Brockschmidt, L\. Peng, C\. Hirnschall, V\. Verma, Y\. Bi, Y\. Xiao, A\. Dabush, K\. Xu, P\. Wallis, R\. Parker, Q\. Wang, Y\. Xu, I\. Safarli, D\. Tewari, Y\. Zhang, S\. Kim, A\. Gesmundo, M\. Thomas, S\. Levi, A\. Chowdhury, K\. Rao, P\. Garst, S\. Conway\-Rahman, H\. Ran, K\. McKinney, Z\. Xiao, W\. Yu, R\. Agrawal, A\. Stjerngren, C\. Ionescu, J\. Chen, V\. Sharma, J\. Chiu, F\. Liu, K\. Franko, C\. Sanford, X\. Cai, P\. Michel, S\. Ganapathy, J\. Labanowski, Z\. Garrett, B\. Vargas, S\. Sun, B\. Gale, T\. Buschmann, G\. Desjardins, N\. Ghelani, P\. Jain, M\. Verma, C\. Asawaroengchai, J\. Eisenschlos, J\. Harlalka, H\. Kazawa, D\. Metzler, J\. Howland, Y\. Jian, J\. Ades, V\. Shah, T\. Gangwani, S\. Lee, R\. Ring, S\. M\. Hernandez, D\. Reich, A\. Sinha, A\. Sathe, J\. Kovac, A\. Gill, A\. Kannan, A\. D’olimpio, M\. Sevenich, J\. Whang, B\. Kim, K\. C\. Sim, J\. Chen, J\. Zhang, S\. Lall, Y\. Matias, B\. Jia, A\. Friesen, S\. Nasso, A\. Thapliyal, B\. Perozzi, T\. Yu, A\. Shekhawat, S\. Huda, P\. Grabowski, E\. Wang, A\. Sreevatsa, H\. Dib, M\. Hassen, P\. Schuh, V\. Milutinovic, C\. Welty, M\. Quinn, A\. Shah, B\. Wang, G\. Barth\-Maron, J\. Frye, N\. Axelsson, T\. Zhu, Y\. Ma, I\. Giannoumis, H\. Sedghi, C\. Ye, Y\. Luan, K\. Aydin, B\. Chandra, V\. Sampathkumar, R\. Huang, V\. Lavrenko, A\. Eleryan, Z\. Hong, S\. Hansen, S\. M\. Carthy, B\. Samanta, D\. Ćevid, X\. Wang, F\. Li, M\. Voznesensky, M\. Hoffman, A\. Terzis, V\. Sehwag, G\. Fidel, L\. He, M\. Cai, Y\. He, A\. Feng, M\. Nikoltchev, S\. Phatale, J\. Chase, R\. Lawton, M\. Zhang, T\. Ouyang, M\. Tragut, M\. H\. Manshadi, A\. Narayanan, J\. Shen, X\. Gao, T\. Bolukbasi, N\. Roy, X\. Li, D\. Golovin, L\. Panait, Z\. Qin, G\. Han, T\. Anthony, S\. Kudugunta, V\. Patraucean, A\. Ray, X\. Chen, X\. Yang, T\. Bhatia, P\. Talluri, A\. Morris, A\. Ražnatović, B\. Brownfield, J\. An, S\. Peng, P\. Kane, C\. Zheng, N\. Duduta, J\. Kessinger, J\. Noraky, S\. Liu, K\. Rong, P\. Veličković, K\. Rush, A\. Goldin, F\. Wei, S\. M\. R\. Garlapati, C\. Pantofaru, O\. Kwon, J\. Ni, E\. Noland, J\. D\. Trapani, F\. Beaufays, A\. G\. Roy, Y\. Chow, A\. Turker, G\. Cideron, L\. Mei, J\. Clark, Q\. Dou, M\. Bošnjak, R\. Leith, Y\. Du, A\. Yazdanbakhsh, M\. Nasr, C\. Kwak, S\. S\. Sheth, A\. Kaskasoli, A\. Anand, B\. Lakshminarayanan, S\. Jerome, D\. Bieber, C\. Chu, A\. Senges, T\. Shen, M\. Sridhar, N\. Ndebele, B\. Beyret, S\. Mohamed, M\. Chen, M\. Freitag, J\. Guo, L\. Liu, P\. Roit, H\. Chen, S\. Yan, T\. Stone, J\. Co\-Reyes, J\. Cole, S\. Scellato, S\. Azizi, H\. Hashemi, A\. Jin, A\. Iyer, M\. Valentine, A\. György, A\. Ahuja, D\. H\. Diaz, C\. Lee, N\. Clement, W\. Kong, D\. Garmon, I\. Watts, K\. Bhatia, K\. Gupta, M\. Miecnikowski, H\. Vallet, A\. Taly, E\. Loper, S\. Joshi, J\. Atwood, J\. Chick, M\. Collier, F\. Iliopoulos, R\. Trostle, B\. Gunel, R\. Leal\-Cavazos, A\. M\. Hrafnkelsson, M\. Guzman, X\. Ju, A\. Forbes, J\. Emond, K\. Chauhan, B\. Caine, L\. Xiao, W\. Zeng, A\. Moufarek, D\. Murphy, M\. Meng, N\. Gupta, F\. Riedel, A\. Das, E\. Lawal, S\. Narayan, T\. Sosea, J\. Swirhun, L\. Friso, B\. Neyshabur, J\. Lu, S\. Girgin, M\. Wunder, E\. Yvinec, A\. Pyne, V\. Carbune, S\. Rijhwani, Y\. Guo, T\. Doshi, A\. Briukhov, M\. Bain, A\. Hitron, X\. Wang, A\. Gupta, K\. Chen, C\. Du, W\. Zhang, D\. Shah, A\. Akula, M\. Dylla, A\. Kachra, W\. Kuo, T\. Zou, L\. Wang, L\. Xu, J\. Zhu, J\. Snyder, S\. Menon, O\. Firat, I\. Mordatch, Y\. Yuan, N\. Ponomareva, R\. Blevins, L\. Moore, W\. Wang, P\. Chen, M\. Scholz, A\. Dwornik, J\. Lin, S\. Li, D\. Antognini, T\. I, X\. Song, M\. Miller, U\. Kalra, A\. Raveret, O\. Akerlund, F\. Wu, A\. Nystrom, N\. Godbole, T\. Liu, H\. DeBalsi, J\. Zhao, B\. Liu, A\. Caciularu, L\. Lax, U\. Khandelwal, V\. Langston, E\. Bailey, S\. Lattanzi, Y\. Wang, N\. Kovelamudi, S\. Mondal, G\. Guruganesh, N\. Hua, O\. Roval, P\. Wesołowski, R\. Ingale, J\. Halcrow, T\. Sohn, C\. Angermueller, B\. Raad, E\. Stickgold, E\. Lu, A\. Kosik, J\. Xie, T\. Lillicrap, A\. Huang, L\. L\. Zhang, D\. Paulus, C\. Farabet, A\. Wertheim, B\. Wang, R\. Joshi, C\. Ko, Y\. Wu, S\. Agrawal, L\. Lin, X\. Sheng, P\. Sung, T\. Breland\-King, C\. Butterfield, S\. Gawde, S\. Singh, Q\. Zhang, R\. Apte, S\. Shetty, A\. Hutter, T\. Li, E\. Salesky, F\. Lebron, J\. Kanerva, M\. Paganini, A\. Nguyen, R\. Vallu, J\. Peter, S\. Velury, D\. Kao, J\. Hoover, A\. Bortsova, C\. Bishop, S\. Jakobovits, A\. Agostini, A\. Agarwal, C\. Liu, C\. Kwong, S\. Tavakkol, I\. Bica, A\. Greve, A\. GP, J\. Marcus, L\. Hou, T\. Duerig, R\. Moroshko, D\. Lacey, A\. Davis, J\. Amelot, G\. Wang, F\. Kim, T\. Strinopoulos, H\. Wan, C\. L\. Lan, S\. Krishnan, H\. Tang, P\. Humphreys, J\. Bai, I\. H\. Shtacher, D\. Machado, C\. Pang, K\. Burke, D\. Liu, R\. Aravamudhan, Y\. Song, E\. Hirst, A\. Singh, B\. Jou, L\. Bai, F\. Piccinno, C\. K\. Fu, R\. Alazard, B\. Meiri, D\. Winter, C\. Chen, M\. Zhang, J\. Heitkaemper, J\. Lambert, J\. Lee, A\. Frömmgen, S\. Rogulenko, P\. Nair, P\. Niemczyk, A\. Bulyenov, B\. Xu, H\. Shemtov, M\. Zadimoghaddam, S\. Toropov, M\. Wirth, H\. Dai, S\. Gollapudi, D\. Zheng, A\. Kurakin, C\. Lee, K\. Bullard, N\. Serrano, I\. Balazevic, Y\. Li, J\. Schalkwyk, M\. Murphy, M\. Zhang, K\. Sequeira, R\. Datta, N\. Agrawal, C\. Sutton, N\. Attaluri, M\. Chiang, W\. Farhan, G\. Thornton, K\. Lin, T\. Choma, H\. Nguyen, K\. Dasgupta, D\. Robinson, I\. Comşa, M\. Riley, A\. Pillai, B\. Mustafa, B\. Golan, A\. Zandieh, J\. Lespiau, B\. Porter, D\. Ross, S\. Rajayogam, M\. Agarwal, S\. Venugopalan, B\. Shahriari, Q\. Yan, H\. Xu, T\. Tobin, P\. Dubov, H\. Shi, A\. Recasens, A\. Kovsharov, S\. Borgeaud, L\. Dery, S\. Vasanth, E\. Gribovskaya, L\. Qiu, M\. Mahdieh, W\. Skut, E\. Nielsen, C\. Zheng, A\. Yu, C\. G\. Bostock, S\. Gupta, A\. Archer, C\. Rawles, E\. Davies, A\. Svyatkovskiy, T\. Tsai, Y\. Halpern, C\. Reisswig, B\. Wydrowski, B\. Chang, J\. Puigcerver, M\. H\. Taege, J\. Li, E\. Schnider, X\. Li, D\. Dena, Y\. Xu, U\. Telang, T\. Shi, H\. Zen, K\. Kastner, Y\. Ko, N\. Subramaniam, A\. Kumar, P\. Blois, Z\. Dai, J\. Wieting, Y\. Lu, Y\. Zeldes, T\. Xie, A\. Hauth, A\. Ţifrea, Y\. Li, S\. El\-Husseini, D\. Abolafia, H\. Zhou, W\. Ding, S\. Ghalebikesabi, C\. Guía, A\. Maksai, Á\. Weisz, S\. Arik, N\. Sukhanov, A\. Świetlik, X\. Jia, L\. Yu, W\. Wang, M\. Brand, D\. Bloxwich, S\. Kirmani, Z\. Chen, A\. Go, P\. Sprechmann, N\. Kannen, A\. Carin, P\. Sandhu, I\. Edkins, L\. Nooteboom, J\. Gupta, L\. Maggiore, J\. Azizi, Y\. Pritch, P\. Yin, M\. Gupta, D\. Tarlow, D\. Smith, D\. Ivanov, M\. Babaeizadeh, A\. Goel, S\. Kambala, G\. Chu, M\. Kastelic, M\. Liu, H\. Soltau, A\. Stone, S\. Agrawal, M\. Kim, K\. Soparkar, S\. Tadepalli, O\. Bunyan, R\. Soh, A\. Kannan, D\. Kim, B\. J\. Chen, A\. Halumi, S\. Roy, Y\. Wang, O\. Sercinoglu, G\. Gibson, S\. Bhatnagar, M\. Sano, D\. von Dincklage, Q\. Ren, B\. Mitrevski, M\. Olšák, J\. She, C\. Doersch, Jilei, Wang, B\. Liu, Q\. Tan, T\. Yakar, T\. Warkentin, A\. Ramirez, C\. Lebsack, J\. Dillon, R\. Mathews, T\. Cobley, Z\. Wu, Z\. Chen, J\. Simon, S\. Nath, T\. Sainath, A\. Bendebury, R\. Julian, B\. Mankalale, D\. Ćurko, P\. Zacchello, A\. R\. Brown, K\. Sodhia, H\. Howard, S\. Caelles, A\. Gupta, G\. Evans, A\. Bulanova, L\. Katzen, R\. Goldenberg, A\. Tsitsulin, J\. Stanton, B\. Schillings, V\. Kovalev, C\. Fry, R\. Shah, K\. Lin, S\. Upadhyay, C\. Li, S\. Radpour, M\. Maggioni, J\. Xiong, L\. Haas, J\. Brennan, A\. Kamath, N\. Savinov, A\. Nagrani, T\. Yacovone, R\. Kappedal, K\. Andriopoulos, L\. Lao, Y\. Li, G\. Rozhdestvenskiy, K\. Hashimoto, A\. Audibert, S\. Austin, D\. Rodriguez, A\. Ruoss, G\. Honke, D\. Karkhanis, X\. Xiong, Q\. Wei, J\. Huang, Z\. Leng, V\. Premachandran, S\. Bileschi, G\. Evangelopoulos, T\. Mensink, J\. Pavagadhi, D\. Teplyashin, P\. Chang, L\. Xue, G\. Tanzer, S\. Goldman, K\. Patel, S\. Li, J\. Wiesner, I\. Zheng, I\. Stewart\-Binks, J\. Han, Z\. Li, L\. Luo, K\. Lenc, M\. Lučić, F\. Xue, R\. Mullins, A\. Guseynov, C\. Chang, I\. Galatzer\-Levy, A\. Zhang, G\. Bingham, G\. Hu, A\. Hartman, Y\. Ma, J\. Griffith, A\. Irpan, C\. Radebaugh, S\. Yue, L\. Fan, V\. Ungureanu, C\. Sorokin, H\. Teufel, P\. Li, R\. Anil, D\. Paparas, T\. Wang, C\. Lin, H\. Peng, M\. Shum, G\. Petrovic, D\. Brady, R\. Nguyen, K\. Macherey, Z\. Li, H\. Singh, M\. Yenugula, M\. Iinuma, X\. Chen, K\. Kopparapu, A\. Stern, S\. Dave, C\. Thekkath, F\. Perot, A\. Kumar, F\. Li, Y\. Xiao, M\. Bilotti, M\. H\. Bateni, I\. Noble, L\. Lee, A\. Vázquez\-Reina, J\. Salazar, X\. Yang, B\. Wang, E\. Gruzewska, A\. Rao, S\. Raghuram, Z\. Xu, E\. Ben\-David, J\. Mei, S\. Dalmia, Z\. Zhang, Y\. Liu, G\. Bansal, H\. Pankov, S\. Schwarcz, A\. Burns, C\. Chan, S\. Sanghai, R\. Liang, E\. Liang, A\. He, A\. Stuart, A\. Narayanan, Y\. Zhu, C\. Frank, B\. Fatemi, A\. Sabne, O\. Lang, I\. Bhattacharya, S\. Settle, M\. Wang, B\. McMahan, A\. Tacchetti, L\. B\. Soares, M\. Hadian, S\. Cabi, T\. Chung, N\. Putikhin, G\. Li, J\. Chen, A\. Tarango, H\. Michalewski, M\. Kazemi, H\. Masoom, H\. Sheftel, R\. Shivanna, A\. Vadali, R\. Comanescu, D\. Reid, J\. Moore, A\. Neelakantan, M\. Sander, J\. Herzig, A\. Rosenberg, M\. Dehghani, J\. Choi, M\. Fink, R\. Hayes, E\. Ge, S\. Weng, C\. Ho, J\. Karro, K\. Krishna, L\. N\. Thiet, A\. Skerry\-Ryan, D\. Eppens, M\. Andreetto, N\. Sarma, S\. Bonacina, B\. K\. Ayan, M\. Nawhal, Z\. Shan, M\. Dusenberry, S\. Thakoor, S\. Gubbi, D\. D\. Nguyen, R\. Tsarfaty, S\. Albanie, J\. Mitrović, M\. Gandhi, B\. Chen, A\. Epasto, G\. Stephanov, Y\. Jin, S\. Gehman, A\. Amini, J\. Weber, F\. Behbahani, S\. Xu, M\. Allamanis, X\. Chen, M\. Ott, C\. Sha, M\. Jastrzebski, H\. Qi, D\. Greene, X\. Wu, A\. Toki, D\. Vlasic, J\. Shapiro, R\. Kotikalapudi, Z\. Shen, T\. Saeki, S\. Xie, A\. Cassirer, S\. Bharadwaj, T\. Kiyono, S\. Bhojanapalli, E\. Rosenfeld, S\. Ritter, J\. Mao, J\. G\. Oliveira, Z\. Egyed, B\. Bandemer, E\. Parisotto, K\. Kinoshita, J\. Pluto, P\. Maniatis, S\. Li, Y\. Guo, G\. Ghiasi, J\. Tarbouriech, S\. Chatterjee, J\. Jin, Katrina, Xu, J\. Palomaki, S\. Arnold, M\. Sewak, F\. Piccinini, M\. Sharma, B\. Albrecht, S\. Purser\-haskell, A\. Vaswani, C\. Chen, M\. Wisniewski, Q\. Cao, J\. Aslanides, N\. M\. Phu, M\. Sieb, L\. Agubuzu, A\. Zheng, D\. Sohn, M\. Selvi, A\. Andreassen, K\. Subudhi, P\. Eruvbetine, O\. Woodman, T\. Mery, S\. Krause, X\. Ren, X\. Ma, J\. Luo, D\. Chen, W\. Fan, H\. Griffiths, C\. Schuler, A\. Li, S\. Zhang, J\. Sarr, S\. Luo, R\. Patana, M\. Watson, D\. Naboulsi, M\. Collins, S\. Sidhwani, E\. Hoogeboom, S\. Silver, E\. Caveness, X\. Zhao, M\. Rodriguez, M\. Deines, L\. Bai, P\. Griffin, M\. Tagliasacchi, E\. Xue, S\. R\. Babbula, B\. Pang, N\. Ding, G\. Shen, E\. Peake, R\. Crocker, S\. S\. Raghvendra, D\. Swisher, W\. Han, R\. Singh, L\. Wu, V\. Pchelin, T\. Munkhdalai, D\. Alon, G\. Bacon, E\. Robles, J\. Bulian, M\. Johnson, G\. Powell, F\. T\. Ferreira, Y\. Li, F\. Benzing, M\. Velimirović, H\. Soyer, W\. Kong, Tony, Nguyên, Z\. Yang, J\. Liu, J\. van Amersfoort, D\. Gillick, B\. Sun, N\. Rauschmayr, K\. Zhang, S\. Zhan, T\. Zhou, A\. Frolov, C\. Yang, D\. Vnukov, L\. Rouillard, H\. Li, A\. Mandhane, N\. Fallen, R\. Venkataraman, C\. H\. Hu, J\. Brennan, J\. Lee, J\. Chang, M\. Sundermeyer, Z\. Pan, R\. Ke, S\. Tong, A\. Fabrikant, W\. Bono, J\. Gu, R\. Foley, Y\. Mao, M\. Delakis, D\. Bhaswar, R\. Frostig, N\. Li, A\. Zipori, C\. Hope, O\. Kozlova, S\. Mishra, J\. Djolonga, C\. Schiff, M\. A\. Merey, E\. Briakou, P\. Morgan, A\. Wan, A\. Hassidim, R\. Skerry\-Ryan, K\. Sengupta, M\. Jasarevic, P\. Kallakuri, P\. Kunkle, H\. Brennan, T\. Lieber, H\. Mansoor, J\. Walker, B\. Zhang, A\. Xie, G\. Žužić, A\. Chukwuka, A\. Druinsky, D\. Cho, R\. Yao, F\. Naeem, S\. Butt, E\. Kim, Z\. Jia, M\. Jordan, A\. Lelkes, M\. Kurzeja, S\. Wang, J\. Zhao, A\. Over, A\. Chakladar, M\. Prasetya, N\. Jha, S\. Ganapathy, Y\. Cong, P\. Shroff, C\. Saroufim, S\. Miryoosefi, M\. Hammad, T\. Nasir, W\. Xi, Y\. Gao, Y\. Maeng, B\. Hora, C\. Cheng, P\. Haghani, Y\. Lewenberg, C\. Lu, M\. Matysiak, N\. Raisinghani, H\. Wang, L\. Baugher, R\. Sukthankar, M\. Giang, J\. Schultz, N\. Fiedel, M\. Chen, C\. Lee, T\. Dey, H\. Zheng, S\. Paul, C\. Smith, A\. Ly, Y\. Wang, R\. Bansal, B\. Perz, S\. Ricco, S\. Blank, V\. Keshava, D\. Sharma, M\. Chow, K\. Lad, K\. Jalan, S\. Osindero, C\. Swanson, J\. Scott, A\. Ilić, X\. Li, S\. R\. Jonnalagadda, A\. S\. Soudagar, Y\. Xiong, B\. Batsaikhan, D\. Jarrett, N\. Kumar, M\. Shah, M\. Lawlor, A\. Waters, M\. Graham, R\. May, S\. Ramos, S\. Lefdal, Z\. Cankara, N\. Cano, B\. O’Donoghue, J\. Borovik, F\. Liu, J\. Grimstad, M\. Alnahlawi, K\. Tsihlas, T\. Hudson, N\. Grigorev, Y\. Jia, T\. Huang, T\. P\. Igwe, S\. Lebedev, X\. Tang, I\. Krivokon, F\. Garcia, M\. Tan, E\. Jia, P\. Stys, S\. Vashishth, Y\. Liang, B\. Venkatraman, C\. Gu, A\. Kementsietsidis, C\. Zhu, J\. Jung, Y\. Bai, M\. J\. Hosseini, F\. Ahmed, A\. Gupta, X\. Yuan, S\. Ashraf, S\. Nigam, G\. Vasudevan, P\. Awasthi, A\. M\. Gilady, Z\. Mariet, R\. Eskander, H\. Li, H\. Hu, G\. Garrido, P\. Schlattner, G\. Zhang, R\. Saxena, P\. Dević, K\. Muralidharan, A\. Murthy, Y\. Zhou, M\. Choi, A\. Wongpanich, Z\. Wang, P\. Shah, Y\. Xu, Y\. Huang, S\. Spencer, A\. Chen, J\. Cohan, J\. Wang, J\. Tompson, J\. Wu, R\. Haroun, H\. Li, B\. Huergo, F\. Yang, T\. Yin, J\. Wendt, M\. Bendersky, R\. Chaabouni, J\. Snaider, J\. Ferret, A\. Jindal, T\. Thompson, A\. Xue, W\. Bishop, S\. M\. Phal, A\. Sharma, Y\. Sung, P\. Radhakrishnan, M\. Shomrat, R\. Ingle, R\. Vij, J\. Gilmer, M\. D\. Istin, S\. Sobell, Y\. Lu, E\. Nottage, D\. Sadigh, J\. Willcock, T\. Zhang, S\. Xu, S\. Brown, K\. Lee, G\. Wang, Y\. Zhu, Y\. Tay, C\. Kim, A\. Gutierrez, A\. Sharma, Y\. Xian, S\. Seo, C\. Cui, E\. Pochernina, C\. Baetu, K\. Jastrzębski, M\. Ly, M\. Elhawaty, D\. Suh, E\. Sezener, P\. Wang, N\. Yuen, G\. Tucker, J\. Cai, Z\. Yang, C\. Wang, A\. Muzio, H\. Qian, J\. Yoo, D\. Lockhart, K\. R\. McKee, M\. Guo, M\. Mehrotra, A\. Mendonça, S\. V\. Mehta, S\. Ben, C\. Tekur, J\. Mu, M\. Zhu, V\. Krakovna, H\. Lee, A\. Maschinot, S\. Cevey, H\. Choe, A\. Bai, H\. Srinivasan, D\. Gasaway, N\. Young, P\. Siegler, D\. Holtmann\-Rice, V\. Piratla, K\. Baumli, R\. Yogev, A\. Hofer, H\. van Hasselt, S\. Grant, Y\. Chervonyi, D\. Silver, A\. Hogue, A\. Agarwal, K\. Wang, P\. Singh, F\. Flynn, J\. Lipschultz, R\. David, L\. Bellot, Y\. Yang, L\. Le, F\. Graziano, K\. Olszewska, K\. Hui, A\. Maurya, N\. Parotsidis, W\. Chen, T\. Oguntebi, J\. Kelley, A\. Baddepudi, J\. Mauerer, G\. Shaw, A\. Siegman, L\. Yang, S\. Shetty, S\. Roy, Y\. Song, W\. Stokowiec, R\. Burnell, O\. Savant, R\. Busa\-Fekete, J\. Miao, S\. Ghosh, L\. MacDermed, P\. Lippe, M\. Dektiarev, Z\. Behrman, F\. Mentzer, K\. Nguyen, M\. Wei, S\. Verma, C\. Knutsen, S\. Dasari, Z\. Yan, P\. Mitrichev, X\. Wang, V\. Shejwalkar, J\. Austin, S\. Sunkara, N\. Potti, Y\. Virin, C\. Wright, G\. Liu, O\. Riva, E\. Pot, G\. Kochanski, Q\. Le, G\. Balasubramaniam, A\. Dhar, Y\. Liao, A\. Bloniarz, D\. Shukla, E\. Cole, J\. Lee, S\. Zhang, S\. Kafle, S\. Vashishtha, P\. Mahmoudieh, G\. Chen, R\. Hoffmann, P\. Srinivasan, A\. D\. Lago, Y\. B\. Shalom, Z\. Wang, M\. Elabd, A\. Sharma, J\. Oh, S\. Kothawade, M\. Le, M\. Monteiro, S\. Yang, K\. Alarakyia, R\. Geirhos, D\. Mincu, H\. Garnes, H\. Kobayashi, S\. Mariooryad, K\. Krasowiak, Zhixin, Lai, S\. Mourad, M\. Wang, F\. Bu, O\. Aharoni, G\. Chen, A\. Goyal, V\. Zubov, A\. Bapna, E\. Dabir, N\. Kothari, K\. Lamerigts, N\. D\. Cao, J\. Shar, C\. Yew, N\. Kulkarni, D\. Mahaarachchi, M\. Joshi, Z\. Zhu, J\. Lichtarge, Y\. Zhou, H\. Muckenhirn, V\. Selo, O\. Vinyals, P\. Chen, A\. Brohan, V\. Mehta, S\. Cogan, R\. Wang, T\. Geri, W\. Ko, W\. Chen, F\. Viola, K\. Shivam, L\. Wang, M\. C\. Elish, R\. A\. Popa, S\. Pereira, J\. Liu, R\. Koster, D\. Kim, G\. Zhang, S\. Ebrahimi, P\. Talukdar, Y\. Zheng, P\. Poklukar, A\. Mikhalap, D\. Johnson, A\. Vijayakumar, M\. Omernick, M\. Dibb, A\. Dubey, Q\. Hu, A\. Suman, V\. Aggarwal, I\. Kornakov, F\. Xia, W\. Lowe, A\. Kolganov, T\. Xiao, V\. Nikolaev, S\. Hemingray, B\. Li, J\. Iljazi, M\. Rybiński, B\. Sandhu, P\. Lu, T\. Luong, R\. Jenatton, V\. Govindaraj, Hui, Li, G\. Dulac\-Arnold, W\. Park, H\. Wang, A\. Modi, J\. Pouget\-Abadie, K\. Greller, R\. Gupta, R\. Berry, P\. Ramachandran, J\. Xie, L\. McCafferty, J\. Wang, K\. Gupta, H\. Lim, B\. Bratanič, A\. Brock, I\. Akolzin, J\. Sproch, D\. Karliner, D\. Kim, A\. Goedeckemeyer, N\. Shazeer, C\. Schmid, D\. Calandriello, P\. Bhatia, K\. Choromanski, C\. Montgomery, D\. Dua, A\. Ramalho, H\. King, Y\. Gao, L\. Nguyen, D\. Lindner, D\. Pitta, O\. Johnson, K\. Salama, D\. Ardila, M\. Han, E\. Farnese, S\. Odoom, Z\. Wang, X\. Ding, N\. Rink, R\. Smith, H\. T\. Lehri, E\. Cohen, N\. Vats, T\. He, P\. Gopavarapu, A\. Paszke, M\. Patel, W\. V\. Gansbeke, L\. Loher, L\. Castro, M\. Voitovich, T\. von Glehn, N\. George, S\. Niklaus, Z\. Eaton\-Rosen, N\. Rakićević, E\. Jue, S\. Perel, C\. Zhang, Y\. Bahat, A\. Pouget, Z\. Xing, F\. Huot, A\. Shenoy, T\. Bos, V\. Coriou, B\. Richter, N\. Noy, Y\. Wang, S\. Ontanon, S\. Qin, G\. Makarchuk, D\. Hassabis, Z\. Li, M\. Sharma, K\. Venkatesan, I\. Kemaev, R\. Daniel, S\. Huang, S\. Shah, O\. Ponce, Warren, Chen, M\. Faruqui, J\. Wu, S\. Andačić, S\. Payrits, D\. McDuff, T\. Hume, Y\. Cao, M\. Tessler, Q\. Wang, Y\. Wang, I\. Rendulic, E\. Agustsson, M\. Johnson, T\. Lando, A\. Howard, S\. G\. S\. Padmanabhan, M\. Daswani, A\. Banino, M\. Kilgore, J\. Heek, Z\. Ji, A\. Caceres, C\. Li, N\. Kassner, A\. Vlaskin, Z\. Liu, A\. Grills, Y\. Hou, R\. Sukkerd, G\. Cheon, N\. Shetty, L\. Markeeva, P\. Stanczyk, T\. Iyer, Y\. Gong, S\. Gao, K\. Gopalakrishnan, T\. Blyth, M\. Reynolds, A\. Bhoopchand, M\. Bilenko, D\. Gharibian, V\. Zayats, A\. Faust, A\. Singh, M\. Ma, H\. Jiao, S\. Vijayanarasimhan, L\. Aroyo, V\. Yadav, S\. Chakera, A\. Kakarla, V\. Meshram, K\. Gregor, G\. Botea, E\. Senter, D\. Jia, G\. Kovacs, N\. Sharma, S\. Baur, K\. Kang, Y\. He, L\. Zhuo, M\. Kostelac, I\. Laish, S\. Peng, L\. O’Bryan, D\. Kasenberg, G\. R\. Rao, E\. Leurent, B\. Zhang, S\. Stevens, A\. Salazar, Y\. Zhang, I\. Lobov, J\. Walker, A\. Porter, M\. Redshaw, H\. Ke, A\. Rao, A\. Lee, H\. Lam, M\. Moffitt, J\. Kim, S\. Qiao, T\. Koo, R\. Dadashi, X\. Song, M\. Sundararajan, P\. Xu, C\. Kawamoto, Y\. Zhong, C\. Barbu, A\. Reddy, M\. Verzetti, L\. Li, G\. Papamakarios, H\. Klimczak\-Plucińska, M\. Cassin, K\. Kavukcuoglu, R\. Swavely, A\. Vaucher, J\. Zhao, R\. Hemsley, M\. Tschannen, H\. Ge, G\. Menghani, Y\. Yu, N\. Ha, W\. He, X\. Wu, M\. Song, R\. Sterneck, S\. Zinke, D\. A\. Calian, A\. Marsden, A\. C\. Ruiz, M\. Hessel, A\. Gueta, B\. Lee, B\. Farris, M\. Gupta, Y\. Li, M\. Saleh, V\. Misra, K\. Xiao, P\. Mendolicchio, G\. Buttimore, V\. Krayvanova, N\. Nayakanti, M\. Wiethoff, Y\. Pande, A\. Mirhoseini, N\. Lao, J\. Liu, Y\. Hua, A\. Chen, Y\. Malkov, D\. Kalashnikov, S\. Gupta, K\. Audhkhasi, Y\. Zhai, S\. Kopalle, P\. Jain, E\. Ofek, C\. Meyer, K\. Baatarsukh, H\. Strejček, J\. Qian, J\. Freedman, R\. Figueira, M\. Sokolik, O\. Bachem, R\. Lin, D\. Kharrat, C\. Hidey, P\. Xu, D\. Duan, Y\. Li, M\. Ersoy, R\. Everett, K\. Cen, R\. Santamaria\-Fernandez, A\. Taubenfeld, I\. Mackinnon, L\. Deng, P\. Zablotskaia, S\. Viswanadha, S\. Goel, D\. Yates, Y\. Deng, P\. Choy, M\. Chen, A\. Sinha, A\. Mossin, Y\. Wang, A\. Szlam, S\. Hao, P\. K\. Rubenstein, M\. Toksoz\-Exley, M\. Aperghis, Y\. Zhong, J\. Ahn, M\. Isard, O\. Lacombe, F\. Luisier, C\. Anastasiou, Y\. Kalley, U\. Prabhu, E\. Dunleavy, S\. Bijwadia, J\. Mao\-Jones, K\. Chen, R\. Pasumarthi, E\. Wood, A\. Dostmohamed, N\. Hurley, J\. Simsa, A\. Parrish, M\. Pajarskas, M\. Harvey, O\. Skopek, Y\. Kochinski, J\. Rey, V\. Rieser, D\. Zhou, S\. J\. Lee, T\. Acharya, G\. Li, J\. Jiang, X\. Zhang, B\. Gipson, E\. Mahintorabi, M\. Gelmi, N\. Khajehnouri, A\. Yeh, K\. Lee, L\. Matthey, L\. Baker, T\. Pham, H\. Fu, A\. Pak, P\. Gupta, C\. Vasconcelos, A\. Sadovsky, B\. Walker, S\. Hsiao, P\. Zochbauer, A\. Marzoca, N\. Velan, J\. Zeng, G\. Baechler, D\. Driess, D\. Jain, Y\. Huang, L\. Tao, J\. Maggs, N\. Levine, J\. Schneider, E\. Gemzer, S\. Petit, S\. Han, Z\. Fisher, D\. Zelle, C\. Biles, E\. Ie, A\. Fadeeva, C\. Liu, J\. V\. Franco, A\. Collister, H\. Zhang, R\. Wang, R\. Zhao, L\. Kieliger, K\. Shuster, R\. Zhu, B\. Gong, L\. Chan, R\. Sun, S\. Basu, R\. Zimmermann, J\. Hayes, A\. Bapna, J\. Snoek, W\. Yang, P\. Datta, J\. A\. Abdallah, K\. Kilgour, L\. Li, S\. Mah, Y\. Jun, M\. Rivière, A\. Karmarkar, T\. Spalink, T\. Huang, L\. Gonzalez, D\. Tran, A\. Nowak, J\. Palowitch, M\. Chadwick, E\. Talius, H\. Mehta, T\. Sellam, P\. Fränken, M\. Nicosia, K\. He, A\. Kini, D\. Amos, S\. Basu, H\. Jobe, E\. Shaw, Q\. Xu, C\. Evans, D\. Ikeda, C\. Yan, L\. Jin, L\. Wang, S\. Yadav, I\. Labzovsky, R\. Sampath, A\. Ma, C\. Schumann, A\. Siddhant, R\. Shah, J\. Youssef, R\. Agarwal, N\. Dabney, A\. Tonioni, M\. Ambar, J\. Li, I\. Guyon, B\. Li, D\. Soergel, B\. Fang, G\. Karadzhov, C\. Udrescu, T\. Trinh, V\. Raunak, S\. Noury, D\. Guo, S\. Gupta, M\. Finkelstein, D\. Petek, L\. Liang, G\. Billock, P\. Sun, D\. Wood, Y\. Song, X\. Yu, T\. Matejovicova, R\. Cohen, K\. Andra, D\. D’Ambrosio, Z\. Deng, V\. Nallatamby, E\. Songhori, R\. Dangovski, A\. Lampinen, P\. Botadra, A\. Hillier, J\. Cao, N\. Baddi, A\. Kuncoro, T\. Yoshino, A\. Bhagatwala, M\. Ranzato, R\. Schaeffer, T\. Liu, S\. Ye, O\. Sarvana, J\. Nham, C\. Kuang, I\. Gao, J\. Baek, S\. Mittal, A\. Wahid, A\. Gergely, B\. Ni, J\. Feldman, C\. Muir, P\. Lamblin, W\. Macherey, E\. Dyer, L\. Kilpatrick, V\. Campos, M\. Bhutani, S\. Fort, Y\. Ahmad, A\. Severyn, K\. Chatziprimou, O\. Ferludin, M\. Dimarco, A\. Kusupati, J\. Heyward, D\. Bahir, K\. Villela, K\. Millican, D\. Marcus, S\. Bahargam, C\. Unlu, N\. Roth, Z\. Wei, S\. Gopal, D\. Ghoshal, E\. Lee, S\. Lin, J\. Lees, D\. Lee, A\. Hosseini, C\. Fan, S\. Neel, M\. Wu, Y\. Altun, H\. Cai, E\. Piqueras, J\. Woodward, A\. Bissacco, S\. Haykal, M\. Bordbar, P\. Sundaram, S\. Hodkinson, D\. Toyama, G\. Polovets, A\. Myers, A\. Sinha, T\. Levinboim, K\. Krishnakumar, R\. Chhaparia, T\. Sholokhova, N\. B\. Gundavarapu, G\. Jawahar, H\. Qureshi, J\. Hu, N\. Momchev, M\. Rahtz, R\. Wu, A\. P\. S, K\. Dhamdhere, M\. Guo, U\. Gupta, A\. Eslami, M\. Schain, M\. Blokzijl, D\. Welling, D\. Orr, L\. Bolelli, N\. Perez\-Nieves, M\. Sirotenko, A\. Prasad, A\. Kar, B\. D\. B\. Pigem, T\. Terzi, G\. Weisz, D\. Ghosh, A\. Mavalankar, D\. Madeka, K\. Daugaard, H\. Adam, V\. Shah, D\. Berman, M\. Tran, S\. Baker, E\. Andrejczuk, G\. Chole, G\. Raboshchuk, M\. Mirzazadeh, T\. Kagohara, S\. Wu, C\. Schallhart, B\. Orlando, C\. Wang, A\. Rrustemi, H\. Xiong, H\. Liu, A\. Vezer, N\. Ramsden, S\. Chang, S\. Mudgal, Y\. Li, N\. Vieillard, Y\. Hoshen, F\. Ahmad, A\. Slone, A\. Hua, N\. Potikha, M\. Rossini, J\. Stritar, S\. Prakash, Z\. Wang, X\. Dong, A\. Nazari, E\. Nehoran, K\. Tekelioglu, Y\. Li, K\. Badola, T\. Funkhouser, Y\. Li, V\. Yerram, R\. Ganeshan, D\. Formoso, K\. Langner, T\. Shi, H\. Li, Y\. Yamamori, A\. Panda, A\. Saade, A\. S\. Scarpati, C\. Breaux, C\. Carey, Z\. Zhou, C\. Hsieh, S\. Bridgers, A\. Butryna, N\. Gupta, V\. Tulsyan, S\. Woo, E\. Eltyshev, W\. Grathwohl, C\. Parks, S\. Benjamin, R\. Panigrahy, S\. Dodhia, D\. D\. Freitas, C\. Sauer, W\. Song, F\. Alet, J\. Tolins, C\. Paduraru, X\. Zhou, B\. Albert, Z\. Zhang, L\. Shu, M\. Bansal, S\. Nguyen, A\. Globerson, O\. Xiao, J\. Manyika, T\. Hennigan, R\. Rong, J\. Matak, A\. Bakalov, A\. Sharma, D\. Sinopalnikov, A\. Pierson, S\. Roller, G\. Brown, M\. Gao, T\. Fukuzawa, A\. Ghafouri, K\. Vassigh, I\. Barr, Z\. Wang, A\. Korsun, R\. Jayaram, L\. Ren, T\. Zaman, S\. Khan, Y\. Lunts, D\. Deutsch, D\. Uthus, N\. Katz, M\. Samsikova, A\. Khalifa, N\. Sethi, J\. Sun, L\. Tang, U\. Alon, X\. Luo, D\. Yu, A\. Nayyar, B\. Petrini, W\. Truong, V\. Hellendoorn, N\. Chinaev, C\. Alberti, W\. Wang, J\. Hu, V\. Mirrokni, A\. Balashankar, A\. Aharon, A\. Mehta, A\. Iscen, J\. Kready, L\. Manning, A\. Mohananey, Y\. Chen, A\. Tripathi, A\. Wu, I\. Petrovski, D\. Hwang, M\. Baeuml, S\. Chandrakaladharan, Y\. Liu, R\. Coaguila, M\. Chen, S\. Ma, P\. Tafti, S\. Tatineni, T\. Spitz, J\. Ye, P\. Vicol, M\. Rosca, A\. Puigdomènech, Z\. Yahav, S\. Ghemawat, H\. Lin, P\. Kirk, Z\. Nabulsi, S\. Brin, B\. Bohnet, K\. Caluwaerts, A\. S\. Veerubhotla, D\. Zheng, Z\. Dai, P\. Petrov, Y\. Xu, R\. Mehran, Z\. Xu, L\. Zintgraf, J\. Choi, S\. A\. Hombaiah, R\. Thoppilan, S\. Reddi, L\. Lew, L\. Li, K\. Webster, K\. Sawhney, L\. Lamprou, S\. Shakeri, M\. Lunayach, J\. Chen, S\. Bagri, A\. Salcianu, Y\. Chen, Y\. Donchev, C\. Magister, S\. Nørly, V\. Rodrigues, T\. Izo, H\. Noga, J\. Zou, T\. Köppe, W\. Zhou, K\. Lee, X\. Long, D\. Eisenbud, A\. Chen, C\. Schenck, C\. M\. To, P\. Zhong, E\. Taropa, M\. Truong, O\. Levy, D\. Martins, Z\. Zhang, C\. Semturs, K\. Zhang, A\. Yakubovich, P\. Moreno, L\. McConnaughey, D\. Lu, S\. Redmond, L\. Weerts, Y\. Bitton, T\. Refice, N\. Lacasse, A\. Conmy, C\. Tallec, J\. Odell, H\. Forbes\-Pollard, A\. Socala, J\. Hoech, P\. Kohli, A\. Walton, R\. Wang, M\. Sazanovich, K\. Zhu, A\. Kapishnikov, R\. Galt, M\. Denton, B\. Murdoch, C\. Sikora, K\. Mohamed, W\. Wei, U\. First, T\. McConnell, L\. C\. Cobo, J\. Qin, T\. Avrahami, D\. Balle, Y\. Watanabe, A\. Louis, A\. Kraft, S\. Ariafar, Y\. Gu, E\. Rives, C\. Yoon, A\. Rusu, J\. Cobon\-Kerr, C\. Hahn, J\. Luo, Yuvein, Zhu, N\. Ahuja, R\. Benenson, R\. L\. Kaufman, H\. Yu, L\. Hightower, J\. Zhang, D\. Ni, L\. A\. Hendricks, G\. Wang, G\. Yona, L\. Jain, P\. Barrio, S\. Bhupatiraju, S\. Velusamy, A\. Dafoe, S\. Riedel, T\. Thomas, Z\. Yuan, M\. Bellaiche, S\. Panthaplackel, K\. Kloboves, S\. Jauhari, C\. Akbulut, T\. Davchev, E\. Gladchenko, D\. Madras, A\. Chuklin, T\. Hill, Q\. Yuan, M\. Madhavan, L\. Leonhard, D\. Scandinaro, Q\. Chen, N\. Niu, A\. Douillard, B\. Damoc, Y\. Onoe, F\. Pedregosa, F\. Bertsch, C\. Leichner, J\. Pagadora, J\. Malmaud, S\. Ponda, A\. Twigg, O\. Duzhyi, J\. Shen, M\. Wang, R\. Garg, J\. Chen, U\. Evci, J\. Lee, L\. Liu, K\. Kojima, M\. Yamaguchi, A\. Rajendran, A\. Piergiovanni, V\. K\. Rajendran, M\. Fornoni, G\. Ibagon, H\. Ragan, S\. M\. Khan, J\. Blitzer, A\. Bunner, G\. Sun, T\. Kosakai, S\. Lundberg, N\. Elue, K\. Guu, S\. Park, J\. Park, A\. Narayanaswamy, C\. Wu, J\. Mudigonda, T\. Cohn, H\. Mu, R\. Kumar, L\. Graesser, Y\. Zhang, R\. Killam, V\. Zhuang, M\. Giménez, W\. A\. Jishi, R\. Ley\-Wild, A\. Zhai, K\. Osawa, D\. Cedillo, J\. Liu, M\. Upadhyay, M\. Sieniek, R\. Sharma, T\. Paine, A\. Angelova, S\. Addepalli, C\. Parada, K\. Majumder, A\. Lamp, S\. Kumar, X\. Deng, A\. Myaskovsky, T\. Sabolić, J\. Dudek, S\. York, F\. de Chaumont Quitry, J\. Nie, D\. Cattle, A\. Gunjan, B\. Piot, W\. Khawaja, S\. Bang, S\. Wang, S\. Khodadadeh, R\. R, P\. Rawlani, R\. Powell, K\. Lee, J\. Griesser, G\. Oh, C\. Magalhaes, Y\. Li, S\. Tokumine, H\. N\. Vogel, D\. Hsu, A\. BC, D\. Jindal, M\. Cohen, Z\. Yang, J\. Yuan, D\. de Cesare, T\. Bruguier, J\. Xu, M\. Roy, A\. Jacovi, D\. Belov, R\. Arya, P\. Meadowlark, S\. Cohen\-Ganor, W\. Ye, P\. Morris\-Suzuki, P\. Banzal, G\. Song, P\. Ponnuramu, F\. Zhang, G\. Scrivener, S\. Zaiem, A\. R\. Rochman, K\. Han, B\. Ghazi, K\. Lee, S\. Drath, D\. Suo, A\. Girgis, P\. Shenoy, D\. Nguyen, D\. Eck, S\. Gupta, L\. Yan, J\. Carreira, A\. Gulati, R\. Sang, D\. Mirylenka, E\. Cooney, E\. Chou, M\. Ling, C\. Fan, B\. Coleman, G\. Tubone, R\. Kumar, J\. Baldridge, F\. Hernandez\-Campos, A\. Lazaridou, J\. Besley, I\. Yona, N\. Bulut, Q\. Wellens, A\. Pierigiovanni, J\. George, R\. Green, P\. Han, C\. Tao, G\. Clark, C\. You, A\. Abdolmaleki, J\. Fu, T\. Chen, A\. Chaugule, A\. Chandorkar, A\. Rahman, W\. Thompson, P\. Koanantakool, M\. Bernico, J\. Ren, A\. Vlasov, S\. Vassilvitskii, M\. Kula, Y\. Liang, D\. Kim, Y\. Huang, C\. Ye, D\. Lepikhin, and W\. Helmholz \(2025\)Gemini 2\.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities\.External Links:2507\.06261,[Link](https://arxiv.org/abs/2507.06261)Cited by:[§1](https://arxiv.org/html/2605.30472#S1.p3.2),[§3\.2](https://arxiv.org/html/2605.30472#S3.SS2.SSS0.Px1.p1.1)\.
- Y\. Dai, H\. Chen, J\. Du, R\. Wang, S\. Chen, H\. Wang, and C\. Lee \(2024\)A study of dropout\-induced modality bias on robustness to missing video frames for audio\-visual speech recognition\.pp\. 27445–27455\.Cited by:[§2](https://arxiv.org/html/2605.30472#S2.SS0.SSS0.Px3.p1.1)\.
- A\. DiChristofano, H\. Shuster, S\. Chandra, and N\. Patwari \(2023\)Global performance disparities between english\-language accents in automatic speech recognition\.External Links:2208\.01157,[Link](https://arxiv.org/abs/2208.01157)Cited by:[§4](https://arxiv.org/html/2605.30472#S4.p1.1)\.
- Z\. El Idrissi, M\. Chadi, and S\. Mouchawrab \(2025\)Deep learning for video captioning: a review\.pp\. 335–346\.Cited by:[§1](https://arxiv.org/html/2605.30472#S1.p1.1)\.
- S\. Fu, tyler bonnen, D\. Guillory, and T\. Darrell \(2025\)Hidden in plain sight: VLMs overlook their visual representations\.External Links:[Link](https://openreview.net/forum?id=qQb1JLrwol)Cited by:[§2](https://arxiv.org/html/2605.30472#S2.SS0.SSS0.Px3.p1.1)\.
- L\. A\. Hendricks, K\. Burns, K\. Saenko, T\. Darrell, and A\. Rohrbach \(2018\)Women also snowboard: overcoming bias in captioning models\.Cham,pp\. 793–811\.External Links:ISBN 978\-3\-030\-01219\-9Cited by:[§2](https://arxiv.org/html/2605.30472#S2.SS0.SSS0.Px2.p1.1)\.
- M\. Kamruzzaman, A\. C\. Curry, A\. Cercas Curry, and F\. M\. Plaza\-del\-Arco \(2025\)Seeing race, feeling bias: emotion stereotyping in multimodal language models\.Suzhou, China,pp\. 7317–7351\.External Links:[Link](https://aclanthology.org/2025.findings-emnlp.386/),[Document](https://dx.doi.org/10.18653/v1/2025.findings-emnlp.386),ISBN 979\-8\-89176\-335\-7Cited by:[§2](https://arxiv.org/html/2605.30472#S2.SS0.SSS0.Px3.p1.1)\.
- O\. Kang and D\. L\. Rubin \(2009\)Reverse linguistic stereotyping: measuring the effect of listener expectations on speech evaluation\.Journal of Language and Social Psychology28\(4\),pp\. 441–456\.External Links:[Document](https://dx.doi.org/10.1177/0261927X09341950),[Link](https://doi.org/10.1177/0261927X09341950),https://doi\.org/10\.1177/0261927X09341950Cited by:[§1](https://arxiv.org/html/2605.30472#S1.p2.1)\.
- J\. S\. Kim, K\. Y\. Thu, J\. Ismayilzada, J\. Park, E\. Kim, H\. Ahmad, N\. M\. An, J\. Thorne, and A\. Oh \(2025\)WHEN TOM EATS KIMCHI: evaluating cultural awareness of multimodal large language models in cultural mixture contexts\.Albuquerque, New Mexico,pp\. 143–154\.External Links:[Link](https://aclanthology.org/2025.c3nlp-1.11/),[Document](https://dx.doi.org/10.18653/v1/2025.c3nlp-1.11),ISBN 979\-8\-89176\-237\-4Cited by:[§2](https://arxiv.org/html/2605.30472#S2.SS0.SSS0.Px3.p1.1)\.
- A\. Koenecke, A\. Nam, E\. Lake, J\. Nudell, M\. Quartey, Z\. Mengesha, C\. Toups, J\. R\. Rickford, D\. Jurafsky, and S\. Goel \(2020\)Racial disparities in automated speech recognition\.Proceedings of the National Academy of Sciences117\(14\),pp\. 7684–7689\.External Links:[Document](https://dx.doi.org/10.1073/pnas.1915768117),[Link](https://www.pnas.org/doi/abs/10.1073/pnas.1915768117),https://www\.pnas\.org/doi/pdf/10\.1073/pnas\.1915768117Cited by:[§1](https://arxiv.org/html/2605.30472#S1.p2.1),[§2](https://arxiv.org/html/2605.30472#S2.SS0.SSS0.Px2.p1.1)\.
- E\. Kutlu \(2023\)Now you see me, now you mishear me: raciolinguistic accounts of speech perception in different english varieties\.Journal of Multilingual and Multicultural Development44\(6\),pp\. 511–525\.External Links:[Document](https://dx.doi.org/10.1080/01434632.2020.1835929),[Link](https://doi.org/10.1080/01434632.2020.1835929),https://doi\.org/10\.1080/01434632\.2020\.1835929Cited by:[§1](https://arxiv.org/html/2605.30472#S1.p2.1),[§2](https://arxiv.org/html/2605.30472#S2.SS0.SSS0.Px1.p1.1),[§3\.1](https://arxiv.org/html/2605.30472#S3.SS1.p1.1)\.
- A\. Lakshmi, B\. Wittenbrink, J\. Correll, and D\. S\. Ma \(2021\)The india face set: international and cultural boundaries impact face impressions and perceptions of category membership\.Frontiers in PsychologyVolume 12 \- 2021\.External Links:[Link](https://www.frontiersin.org/journals/psychology/articles/10.3389/fpsyg.2021.627678),[Document](https://dx.doi.org/10.3389/fpsyg.2021.627678),ISSN 1664\-1078Cited by:[§3\.1](https://arxiv.org/html/2605.30472#S3.SS1.SSS0.Px1.p1.1)\.
- H\. Liu, C\. Li, Q\. Wu, and Y\. J\. Lee \(2023\)Visual instruction tuning\.pp\. 34892–34916\.External Links:[Link](https://proceedings.neurips.cc/paper_files/paper/2023/file/6dcf277ea32ce3288914faf369fe6de0-Paper-Conference.pdf)Cited by:[§1](https://arxiv.org/html/2605.30472#S1.p1.1)\.
- D\. S\. Ma, J\. Correll, and B\. Wittenbrink \(2015\)The chicago face database: a free stimulus set of faces and norming data\.Behavior Research Methods47\(4\),pp\. 1122–1135\(en\)\.External Links:ISSN 1554\-3528,[Document](https://dx.doi.org/10.3758/s13428-014-0532-5)Cited by:[§3\.1](https://arxiv.org/html/2605.30472#S3.SS1.SSS0.Px1.p1.1)\.
- N\. Markl \(2022\)Language variation and algorithmic bias: understanding algorithmic bias in british english automatic speech recognition\.New York, NY, USA,pp\. 521–534\.External Links:ISBN 9781450393522,[Link](https://doi.org/10.1145/3531146.3533117),[Document](https://dx.doi.org/10.1145/3531146.3533117)Cited by:[§1](https://arxiv.org/html/2605.30472#S1.SS0.SSS0.Px1.p1.1)\.
- H\. McGurk and J\. MacDonald \(1976\)Hearing lips and seeing voices\.Nature264\(5588\),pp\. 746–748\.External Links:ISSN 1476\-4687,[Document](https://dx.doi.org/10.1038/264746a0)Cited by:[§1](https://arxiv.org/html/2605.30472#S1.p2.1)\.
- Z\. Mengesha, C\. Heldreth, M\. Lahav, J\. Sublewski, and E\. Tuennerman \(2021\)“I don’t think these devices are very culturally sensitive\.”—impact of automated speech recognition errors on african americans\.Frontiers in Artificial IntelligenceVolume 4 \- 2021\.External Links:[Link](https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2021.725911),[Document](https://dx.doi.org/10.3389/frai.2021.725911),ISSN 2624\-8212Cited by:[§1](https://arxiv.org/html/2605.30472#S1.SS0.SSS0.Px1.p1.1)\.
- M\. Ott, S\. Edunov, A\. Baevski, A\. Fan, S\. Gross, N\. Ng, D\. Grangier, and M\. Auli \(2019\)Fairseq: a fast, extensible toolkit for sequence modeling\.pp\. 48–53\.Cited by:[Appendix E](https://arxiv.org/html/2605.30472#A5.p1.1)\.
- K\. R\. Prajwal, R\. Mukhopadhyay, V\. P\. Namboodiri, and C\.V\. Jawahar \(2020\)A lip sync expert is all you need for speech to lip generation in the wild\.InProceedings of the 28th ACM International Conference on Multimedia,MM ’20,New York, NY, USA,pp\. 484–492\.External Links:ISBN 9781450379885,[Link](https://doi.org/10.1145/3394171.3413532),[Document](https://dx.doi.org/10.1145/3394171.3413532)Cited by:[§3\.1](https://arxiv.org/html/2605.30472#S3.SS1.SSS0.Px3.p1.9)\.
- A\. Radford, J\. W\. Kim, C\. Hallacy, A\. Ramesh, G\. Goh, S\. Agarwal, G\. Sastry, A\. Askell, P\. Mishkin, J\. Clark, G\. Krueger, and I\. Sutskever \(2021\)Learning transferable visual models from natural language supervision\.pp\. 8748–8763\.External Links:[Link](https://proceedings.mlr.press/v139/radford21a.html)Cited by:[§1](https://arxiv.org/html/2605.30472#S1.p1.1)\.
- E\. F\. Rodríguez, O\. Perez\-de\-Vinaspre, J\. A\. Campos, D\. Klakow, and V\. Gautam \(2025\)Colombian waitresses y jueces canadienses: gender and country biases in occupation recommendations from LLMs\.Vienna, Austria,pp\. 182–194\.External Links:[Link](https://aclanthology.org/2025.gebnlp-1.18/),[Document](https://dx.doi.org/10.18653/v1/2025.gebnlp-1.18),ISBN 979\-8\-89176\-277\-0Cited by:[§4](https://arxiv.org/html/2605.30472#S4.SS0.SSS0.Px2.p1.1)\.
- A\. Rouditchenko, Y\. Gong, S\. Thomas, L\. Karlinsky, H\. Kuehne, R\. Feris, and J\. Glass \(2024\)Whisper\-Flamingo: Integrating Visual Features into Whisper for Audio\-Visual Speech Recognition and Translation\.InInterspeech 2024,pp\. 2420–2424\.External Links:[Document](https://dx.doi.org/10.21437/Interspeech.2024-322),ISSN 2958\-1796Cited by:[§1](https://arxiv.org/html/2605.30472#S1.p1.1)\.
- A\. Rouditchenko, S\. Thomas, H\. Kuehne, R\. Feris, and J\. Glass \(2025\)MWhisper\-flamingo for multilingual audio\-visual noise\-robust speech recognition\.IEEE Signal Processing Letters32\(\),pp\. 2144–2148\.External Links:[Document](https://dx.doi.org/10.1109/LSP.2025.3569210)Cited by:[§1](https://arxiv.org/html/2605.30472#S1.p1.1),[§1](https://arxiv.org/html/2605.30472#S1.p3.2),[§3\.1](https://arxiv.org/html/2605.30472#S3.SS1.SSS0.Px3.p2.1),[§3\.2](https://arxiv.org/html/2605.30472#S3.SS2.SSS0.Px1.p1.1),[§4](https://arxiv.org/html/2605.30472#S4.SS0.SSS0.Px1.p1.1)\.
- D\. L\. Rubin and K\. A\. Smith \(1990\)Effects of accent, ethnicity, and lecture topic on undergraduates’ perceptions of nonnative english\-speaking teaching assistants\.International Journal of Intercultural Relations14\(3\),pp\. 337–353\.External Links:ISSN 0147\-1767,[Document](https://dx.doi.org/https%3A//doi.org/10.1016/0147-1767%2890%2990019-S)Cited by:[§1](https://arxiv.org/html/2605.30472#S1.p2.1)\.
- D\. L\. Rubin \(1992\)Nonlanguage factors affecting undergraduates’ judgments of nonnative english\-speaking teaching assistants\.Research in Higher Education33\(4\),pp\. 511–531\.External Links:ISSN 1573\-188X,[Document](https://dx.doi.org/10.1007/BF00973770)Cited by:[§1](https://arxiv.org/html/2605.30472#S1.p2.1),[§2](https://arxiv.org/html/2605.30472#S2.SS0.SSS0.Px1.p1.1)\.
- B\. Shi, W\. Hsu, K\. Lakhotia, and A\. Mohamed \(2022\)Learning audio\-visual speech representation by masked multimodal cluster prediction\.arXiv preprint arXiv:2201\.02184\.Cited by:[§1](https://arxiv.org/html/2605.30472#S1.p1.1)\.
- F\. Shu, L\. Zhang, H\. Jiang, and C\. Xie \(2025\)Audio\-Visual LLM for Video Understanding\.InProceedings of the IEEE/CVF International Conference on Computer Vision,pp\. 4246–4255\.Cited by:[§1](https://arxiv.org/html/2605.30472#S1.p1.1)\.
- D\. Snyder, G\. Chen, and D\. Povey \(2015\)Musan: a music, speech, and noise corpus\.arXiv preprint arXiv:1510\.08484\.Cited by:[§3\.1](https://arxiv.org/html/2605.30472#S3.SS1.SSS0.Px3.p2.1)\.
- C\. R\. Steidl and R\. Werum \(2019\)If all you have is a hammer, everything looks like a nail: operationalization matters\.Sociology Compass13\(8\),pp\. e12727\.Note:e12727 SOCO\-1495\.R2External Links:[Document](https://dx.doi.org/https%3A//doi.org/10.1111/soc4.12727),[Link](https://compass.onlinelibrary.wiley.com/doi/abs/10.1111/soc4.12727),https://compass\.onlinelibrary\.wiley\.com/doi/pdf/10\.1111/soc4\.12727Cited by:[Ethics Statement](https://arxiv.org/html/2605.30472#Sx2.p1.1)\.
- W\. H\. Sumby and I\. Pollack \(1954\)Visual contribution to speech intelligibility in noise\.The Journal of the Acoustical Society of America26\(2\),pp\. 212–215\.External Links:ISSN 0001\-4966,[Document](https://dx.doi.org/10.1121/1.1907309)Cited by:[§1](https://arxiv.org/html/2605.30472#S1.p2.1)\.
- R\. Tatman \(2017\)Gender and dialect bias in YouTube’s automatic captions\.InProceedings of the First ACL Workshop on Ethics in Natural Language Processing,D\. Hovy, S\. Spruit, M\. Mitchell, E\. M\. Bender, M\. Strube, and H\. Wallach \(Eds\.\),Valencia, Spain,pp\. 53–59\.External Links:[Link](https://aclanthology.org/W17-1606/),[Document](https://dx.doi.org/10.18653/v1/W17-1606)Cited by:[§2](https://arxiv.org/html/2605.30472#S2.SS0.SSS0.Px2.p1.1)\.
- A\. Wang, S\. Barocas, K\. Laird, and H\. Wallach \(2022\)Measuring representational harms in image captioning\.InProceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency,FAccT ’22,New York, NY, USA,pp\. 324–335\.External Links:ISBN 9781450393522,[Link](https://doi.org/10.1145/3531146.3533099),[Document](https://dx.doi.org/10.1145/3531146.3533099)Cited by:[§1](https://arxiv.org/html/2605.30472#S1.SS0.SSS0.Px1.p1.1)\.
- P\. H\. Westfall and S\. S\. Young \(1993\)Resampling\-based multiple testing: examples and methods for p\-value adjustment\.1 edition,John Wiley & Sons\.Note:Wiley Series in Probability and StatisticsExternal Links:ISBN 0471557617; 9780471557616Cited by:[§3\.2](https://arxiv.org/html/2605.30472#S3.SS2.SSS0.Px2.p2.1)\.
- R\. Wolfe and A\. Caliskan \(2022\)Markedness in visual semantic ai\.InProceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency,FAccT ’22,New York, NY, USA,pp\. 1269–1279\.External Links:ISBN 9781450393522,[Link](https://doi.org/10.1145/3531146.3533183),[Document](https://dx.doi.org/10.1145/3531146.3533183)Cited by:[§2](https://arxiv.org/html/2605.30472#S2.SS0.SSS0.Px2.p1.1)\.
- Y\. Zheng and A\. G\. Samuel \(2017\)Does seeing an asian face make speech sound more accented?\.Attention, Perception, & Psychophysics79\(6\),pp\. 1841–1859\(en\)\.External Links:ISSN 1943\-393X,[Document](https://dx.doi.org/10.3758/s13414-017-1329-2)Cited by:[§1](https://arxiv.org/html/2605.30472#S1.p2.1),[§2](https://arxiv.org/html/2605.30472#S2.SS0.SSS0.Px1.p1.1),[§3\.1](https://arxiv.org/html/2605.30472#S3.SS1.p1.1)\.

## Appendix AAccents in CommonVoice

CommonVoice includes self\-declared accent labels\. First, we lowercase all labels\. All audio files that include “india” in the label, and that exclude “united states” and “england english” are selected as Indian accented audio files for our dataset\. We select all files that include “england english” in the label as UK\-accented data\. Finally, all labels that include “united states english” are counted as US accents\. Through manually inspecting the remaining labels, we confirmed that no other accents were declared\.

## Appendix BQuality Filtering for CommonVoice

CommonVoice data includes audio ratings consisting of up\-votes and down\-votes\. We designed a custom metric to use these ratings to select audios with the highest quality\.

For a given accent, we first weight the up\-votes and down\-votes\. We defineUiU\_\{i\}as the up\-votes for sampleiiandUmaxU\_\{\\text\{max\}\}as the max up\-votes for the accent\. Equivalently, we defineDiD\_\{i\}as the down\-votes for sampleiiandDmaxD\_\{\\text\{max\}\}as the max down\-votes for the accent\.

Finally, we defineU¯i\\bar\{U\}\_\{i\}as the weighted up\-votes for a given sample, andD¯i\\bar\{D\}\_\{i\}as the weighted down\-votes for a given sample, which we calculate as follows:

U¯i:=UiUmax\\bar\{U\}\_\{i\}:=\\frac\{U\_\{i\}\}\{U\_\{\\text\{max\}\}\}\(1\)D¯i:=Dmax−DiDmax\.\\bar\{D\}\_\{i\}:=\\frac\{D\_\{\\text\{max\}\}\-D\_\{i\}\}\{D\_\{\\text\{max\}\}\}\.\(2\)
A higher weighted score represents more up\-votes and fewer down\-votes, respectively\.

We then compute the score of an audio as the harmonic mean of the weighted votes, and take the top 50 with the highest score per accent\.

Score:=2⋅U¯i⋅D¯iU¯i\+D¯i\.\\text\{Score\}:=\\frac\{2\\cdot\\bar\{U\}\_\{i\}\\cdot\\bar\{D\}\_\{i\}\}\{\\bar\{U\}\_\{i\}\+\\bar\{D\}\_\{i\}\}\.\(3\)
Table 3:Static\-face \(no lip\-sync\) absolute WER scores by groupings of faces across gender, ethnicity, and accent\.mWhisper\-F=mWhisper\-Flamingo medium;Gemini=Gemini\-2\.52\.5\-flash\.
## Appendix CFull Results

All WER results with confidence intervals across all splits are shown in Table[4](https://arxiv.org/html/2605.30472#A6.T4)\.

## Appendix DPromptingGemini

We pass two text prompts toGeminitogether with the video or audio: A system prompt and an instruction\. The system prompt was “You are a helpful transcription agent\.”

The instruction for video transcription was “Please transcribe everything that is said in the following video into English\. Output only the transcription\. Prioritize accuracy in transcription, including punctuation and sentence structure, to reflect natural speech flow\. The audio quality may vary from good to quite noisy, please do your best to isolate the main speaker\.” For audio transcription, we replace the word “video” with “audio”\.

## Appendix EWord Error Rate Calculations

We calculate Word Error Rate with the Fairseq\(Ottet al\.,[2019](https://arxiv.org/html/2605.30472#bib.bib43)\)WerScorer, which we initialize as follows:

scorer = WerScorer\(

WerScorerConfig\(wer\_tokenizer="13a",

wer\_remove\_punct=True,

wer\_char\_level=False,

wer\_lowercase=True\)\)

## Appendix FHallucinations and Refusals

Here, we provide some examples of model hallucinations \(output unrelated to input\) in transcriptions, \(partial\) refusals to transcribe, and other unrequested output\.

Table[5](https://arxiv.org/html/2605.30472#A6.T5)provides an example of a hallucination\.

Table 4:All WER results with confidence intervals across all splits\.Table 5:Gemini\-2\.52\.5\-flashhallucinations\.SometimesGeminirefused to transcribe part of the input, replacing parts of the text with some variation of \[unintelligible\]\. Table[6](https://arxiv.org/html/2605.30472#A6.T6)provides an example\.

Table 6:Gemini\-2\.52\.5\-flashpartial refusals\.Geminialso refused to transcribe some audios in full\. Table[7](https://arxiv.org/html/2605.30472#A6.T7)provides some examples\. Sometimes, these descriptions lead to a longer output than the reference text, resulting in a WER higher than 100\.

Table 7:Gemini\-2\.52\.5\-flashfull refusals\.Table[8](https://arxiv.org/html/2605.30472#A6.T8)provides examples ofGeminiadding sound descriptions on top of the transcribed text\.

Table 8:Gemini\-2\.52\.5\-flashsound descriptions\.Table[9](https://arxiv.org/html/2605.30472#A6.T9)provides an example ofGeminirepeating part of the prompt in the output\.

Table 9:Gemini\-2\.52\.5\-flashprompt repetition\.Finally, Table[10](https://arxiv.org/html/2605.30472#A6.T10)provides an example of an unacceptable refusal\.

Table 10:Gemini\-2\.52\.5\-flashunacceptable refusal\.
## Appendix GResults with Static Faces

Tables[3](https://arxiv.org/html/2605.30472#A2.T3)and[11](https://arxiv.org/html/2605.30472#A7.T11)provides an overview of the quality\-of\-service differences for static faces\.

ModelAccentΔ\\DeltaWER \(Max−\-Min\)EthnicityGenderIntersectionNo noise \(SNR=∞=\\infty\)mWFIndian3\.22∗3\.22^\{\{\*\}\}\(Latinx−\-Indian\)0\.360\.36^\{\\phantom\{\*\}\}\(M−\-F\)4\.81∗4\.81^\{\{\*\}\}\(White female−\-Indian female\)mWFUS0\.820\.82^\{\\phantom\{\*\}\}\(Latinx−\-Indian\)0\.220\.22^\{\\phantom\{\*\}\}\(M−\-F\)1\.46∗1\.46^\{\{\*\}\}\(Latinx male−\-Indian female\)mWFUK0\.580\.58^\{\\phantom\{\*\}\}\(Asian−\-Indian\)0\.150\.15^\{\\phantom\{\*\}\}\(M−\-F\)0\.870\.87^\{\\phantom\{\*\}\}\(Asian male−\-Indian male\)GeminiIndian0\.410\.41^\{\\phantom\{\*\}\}\(Indian−\-White\)0\.370\.37^\{\\phantom\{\*\}\}\(F−\-M\)0\.770\.77^\{\\phantom\{\*\}\}\(Latinx female−\-White male\)GeminiUS0\.170\.17^\{\\phantom\{\*\}\}\(Black−\-White\)0\.000\.00^\{\\phantom\{\*\}\}\(n/a\)0\.300\.30^\{\\phantom\{\*\}\}\(Indian female−\-Indian male\)GeminiUK0\.310\.31^\{\\phantom\{\*\}\}\(Asian−\-White\)0\.190\.19^\{\\phantom\{\*\}\}\(F−\-M\)0\.570\.57^\{\\phantom\{\*\}\}\(Asian female−\-White female\)Babble noise \(SNR=5=5\)mWFIndian8\.46∗8\.46^\{\{\*\}\}\(White−\-Black\)0\.540\.54^\{\\phantom\{\*\}\}\(M−\-F\)12\.01∗12\.01^\{\*\}\(White male−\-Black male\)mWFUS1\.75∗1\.75^\{\{\*\}\}\(Latinx−\-Asian\)0\.180\.18^\{\\phantom\{\*\}\}\(F−\-M\)5\.29∗5\.29^\{\*\}\(Black female−\-Black male\)mWFUK2\.12∗2\.12^\{\{\*\}\}\(Latinx−\-Indian\)0\.000\.00^\{\\phantom\{\*\}\}\(n/a\)3\.07∗3\.07^\{\*\}\(Latinx female−\-Indian female\)GeminiIndian0\.550\.55^\{\\phantom\{\*\}\}\(Latinx−\-Indian\)0\.150\.15^\{\\phantom\{\*\}\}\(M−\-F\)0\.770\.77^\{\\phantom\{\*\}\}\(Latinx male−\-Indian female\)GeminiUS3\.31∗3\.31^\{\{\*\}\}\(Asian−\-White\)1\.35∗1\.35^\{\{\*\}\}\(F−\-M\)6\.22∗6\.22^\{\*\}\(Asian female−\-White female\)GeminiUK31\.18∗31\.18^\{\{\*\}\}\(Asian−\-White\)13\.16∗13\.16^\{\{\*\}\}\(F−\-M\)63\.40∗63\.40^\{\*\}\(Asian female−\-Asian male\)Table 11:Static\-face \(no lip\-sync\) largest AVSR quality\-of\-service differences between faces, across ethnicity, gender, and their intersection\. Asterisk \(\*\) denotes statistical significance \(p<0\.005p<0\.005\) according to a permutation test \(Section[3\.2](https://arxiv.org/html/2605.30472#S3.SS2)\)\.mWF=mWhisper\-Flamingo medium;Gemini=Gemini\-2\.52\.5\-flash\. M = Male; F = Female\.
## Appendix HCompute

For our experiments with theWhisper\-Flamingomodel family, we used two NVIDIA RTX A6000 GPUs for approximately 500 hours\. For our experiments withGemini\-2\.52\.5\-flash, we used approximately11B input and output tokens and an Intel\(R\) Xeon\(R\) CPU E5\-2673 v3 @ 2\.40GHz for approximately 400 hours\.

## Appendix IUse of AI Assistants

We used Deepseek to look up statistical analysis references, which were read, corroborated, and verified by hand\. We also used Copilot and Genie for coding support, which was also manually checked\.