conformer

This paper evaluates the 305M-parameter Gemma 4/EmbeddingGemma 2 speech encoder on Saudi and Gulf Arabic ASR without modifying its weights, comparing a frozen CTC reader and an adapter-augmented system against Cohere Transcribe Arabic and other baselines, showing competitive CER and strong efficiency gains. Code and results are publicly released.

该论文提出 MoPE-LoRA，一种基于音素类别（发音方式）而非口音身份组织低秩专家的参数高效适配框架，用于带口音的英语语音识别；在 L2-ARCTIC 上零样本口音评估中相对单 LoRA 提升 12.3%。

Aalto University researchers present a large-scale Finnish speech SSL study using 2.1M hours of raw broadcast audio, showing that ASR confidence-based filtering outperforms LID-based filtering by 3-7% relative WER, along with controlled architectural comparisons of Transformer, Macaron-Net, Conformer, and E-Branchformer at matched parameter budgets.

Oído is an open-source speech recognition system from Lokutor that runs NVIDIA's Conformer-CTC Small (13M params, int8) on a $5 ESP32-S3 microcontroller, outperforming Whisper tiny.en on LibriSpeech and noisy benchmarks with no GPU or NPU.

The paper presents I-Parakeet, an integer-only Conformer ASR model optimized for mobile NPUs, enabling efficient on-device speech recognition.

GigaChat Audio 10B is an audio-native LLM built on GigaChat 3.1 Lightning, integrating a Conformer speech encoder and modality adapter for audio question answering, temporal grounding, and tool use.

Details a method to run a 13 million parameter ASR Conformer model directly on a microcontroller, highlighting advances in edge AI deployment.

This paper introduces GigaAM Multilingual, a Conformer encoder pre-trained on 2M hours of audio with a HuBERT-style objective, addressing data scarcity for Central Asian languages (Kazakh, Kyrgyz, Uzbek). It employs cluster-level data balancing and domain-aware sampling to outperform strong baselines like Whisper Large v3 on target languages.

This paper proposes a multimodal framework that jointly improves Automatic Speech Recognition (ASR) and Dialect Identification (DID) for Indian languages, using a Bottleneck Encoder and RoBERTa with a gating mechanism. Evaluated on eight languages with 33 dialects, it achieves 81.63% DID accuracy and reduces CER/WER to 4.65%/17.73%.

This paper introduces HRVConformer, a hybrid Convolution-Transformer architecture for classifying neonatal hypoxic-ischemic encephalopathy directly from raw heart rate signals, achieving an AUC of 83.23% and outperforming baseline models like ResNet50 and Transformer.

This paper proposes an end-to-end Conformer-based neural decoder for intracortical speech decoding from a participant with ALS, achieving a 23.80% character error rate without any external language model. It demonstrates that meaningful character-level decoding is possible in a fully end-to-end framework.