@shinjiw_at_cmu:我的 Google Scholar h-index 刚刚达到 100!我的第一篇论文发表于 1999 年,这 100 的背后是学生和合作者……
摘要
Shinji Watanabe 宣布他的 Google Scholar h-index 已达 100,并将数十年在语音处理研究与开源工具开发方面的成就归功于他的学生和合作者。该帖子特别提到了 ESPnet、Deep Clustering 和 SUPERB 等奠定现代语音识别基础的里程碑式成果。
查看缓存全文
缓存时间: 2026/10/04 01:04
我的 Google Scholar h-index 刚达到 100 了!🙂
我的第一篇论文发表于 1999 年。这 100 的背后,是学术界和工业界的同学们、合作者们,还有开源社区和各类挑战赛。
这个数字真的属于你们所有人。谢谢大家!🙏
https://t.co/IVGQM30qe8 https://t.co/PUpOCJBMxJ
Shinji Watanabe
来源:https://scholar.google.com/citations?user=U5xRA6QAAAAJ
-
ESPnet:端到端语音处理工具包(https://scholar.google.com/citations?view_op=view_citation&hl=en&user=U5xRA6QAAAAJ&citation_for_view=U5xRA6QAAAAJ:BFeJNCPbDVwC) S Watanabe, T Hori, S Karita, T Hayashi, J Nishitoba, Y Unno, NEY Soplin, ... arXiv preprint arXiv:1804.00015, 2018 2128(2018)
-
Deep clustering:用于分割与分离的判别式嵌入(https://scholar.google.com/citations?view_op=view_citation&hl=en&user=U5xRA6QAAAAJ&citation_for_view=U5xRA6QAAAAJ:_Ybze24A_UAC) JR Hershey, Z Chen, J Le Roux, S Watanabe 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, 2016 1944(2016)
-
SUPERB:语音处理通用性能基准(https://scholar.google.com/citations?view_op=view_citation&hl=en&user=U5xRA6QAAAAJ&citation_for_view=U5xRA6QAAAAJ:RF4BjkDOTHkC) S Yang, PH Chi, YS Chuang, CIJ Lai, K Lakhotia, YY Lin, AT Liu, J Shi, ... arXiv preprint arXiv:2105.01051, 2021 1502(2021)
-
基于联合 CTC-attention 的多任务学习端到端语音识别(https://scholar.google.com/citations?view_op=view_citation&hl=en&user=U5xRA6QAAAAJ&citation_for_view=U5xRA6QAAAAJ:6e4D8M0GhXMC) S Kim, T Hori, S Watanabe 2017 IEEE International Conference on Acoustics, Speech and Signal Processing, 2017 1253(2017)
-
用于端到端语音识别的混合 CTC/attention 架构(https://scholar.google.com/citations?view_op=view_citation&hl=en&user=U5xRA6QAAAAJ&citation_for_view=U5xRA6QAAAAJ:QC-2xSqExF4C) S Watanabe, T Hori, S Kim, JR Hershey, T Hayashi IEEE Journal of Selected Topics in Signal Processing 11 (8), 1240-1253, 2017 1201(2017)
-
语音应用中 Transformer 与 RNN 的对比研究(https://scholar.google.com/citations?view_op=view_citation&hl=en&user=U5xRA6QAAAAJ&citation_for_view=U5xRA6QAAAAJ:vJdfVD8-6ZYC) S Karita, N Chen, T Hayashi, T Hori, H Inaguma, Z Jiang, M Someki, ... 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2019 1088(2019)
-
第三届 CHiME 语音分离与识别挑战赛:数据集、任务与基线(https://scholar.google.com/citations?view_op=view_citation&hl=en&user=U5xRA6QAAAAJ&citation_for_view=U5xRA6QAAAAJ:2KloaMYe4IUC) J Barker, R Marxer, E Vincent, S Watanabe 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 2015 931(2015)
-
基于深度循环神经网络的相位敏感且识别增强的语音分离(https://scholar.google.com/citations?view_op=view_citation&hl=en&user=U5xRA6QAAAAJ&citation_for_view=U5xRA6QAAAAJ:eq2jaN3J8jMC) H Erdogan, JR Hershey, S Watanabe, J Le Roux 2015 IEEE International Conference on Acoustics, Speech and Signal Processing, 2015 872(2015)
-
基于 LSTM 循环神经网络的语音增强及其在噪声鲁棒 ASR 中的应用(https://scholar.google.com/citations?view_op=view_citation&hl=en&user=U5xRA6QAAAAJ&citation_for_view=U5xRA6QAAAAJ:PR6Y55bgFSsC) F Weninger, H Erdogan, S Watanabe, E Vincent, J Le Roux, JR Hershey, ... International Conference on Latent Variable Analysis and Signal Separation, 2015 832(2015)
-
自监督语音表示学习综述(https://scholar.google.com/citations?view_op=view_citation&hl=en&user=U5xRA6QAAAAJ&citation_for_view=U5xRA6QAAAAJ:SSGWEqmz6gUC) A Mohamed, H Lee, L Borgholt, JD Havtorn, J Edin, C Igel, K Kirchhoff, ... IEEE Journal of Selected Topics in Signal Processing 16 (6), 1179-1210, 2022 710(2022)
-
说话人分割聚类综述:深度学习带来的最新进展(https://scholar.google.com/citations?view_op=view_citation&hl=en&user=U5xRA6QAAAAJ&citation_for_view=U5xRA6QAAAAJ:6TexfgwXQfYC) TJ Park, N Kanda, D Dimitriadis, KJ Han, S Watanabe, S Narayanan Computer Speech & Language 72, 101317, 2022 653(2022)
-
基于 deep clustering 的单通道多说话人分离(https://scholar.google.com/citations?view_op=view_citation&hl=en&user=U5xRA6QAAAAJ&citation_for_view=U5xRA6QAAAAJ:H8haQKU-3ZsC) Y Isik, JL Roux, Z Chen, S Watanabe, JR Hershey arXiv preprint arXiv:1607.02173, 2016 569(2016)
-
CHiME-6 挑战赛:面向未切分录音的多说话人语音识别(https://scholar.google.com/citations?view_op=view_citation&hl=en&user=U5xRA6QAAAAJ&citation_for_view=U5xRA6QAAAAJ:5bFWG3eDk9wC) S Watanabe, M Mandel, J Barker, E Vincent, A Arora, X Chang, ... arXiv preprint arXiv:2004.09249, 2020 552(2020)
-
第五届 CHiME 语音分离与识别挑战赛:数据集、任务与基线(https://scholar.google.com/citations?view_op=view_citation&hl=en&user=U5xRA6QAAAAJ&citation_for_view=U5xRA6QAAAAJ:6B7w4NK6UsoC) J Barker, S Watanabe, E Vincent, J Trmal arXiv preprint arXiv:1803.10609, 2018 539(2018)
-
端到端语音识别综述(https://scholar.google.com/citations?view_op=view_citation&hl=en&user=U5xRA6QAAAAJ&citation_for_view=U5xRA6QAAAAJ:auQHJw8QJBgC) R Prabhavalkar, T Hori, TN Sainath, R Schlüter, S Watanabe IEEE/ACM Transactions on Audio, Speech, and Language Processing 32, 325-351, 2023 514(2023)
-
Gigaspeech:拥有 10,000 小时转写音频、持续演进的多领域 ASR 语料库(https://scholar.google.com/citations?view_op=view_citation&hl=en&user=U5xRA6QAAAAJ&citation_for_view=U5xRA6QAAAAJ:UO6ax3c-pNsC) G Chen, S Chai, G Wang, J Du, WQ Zhang, C Weng, D Su, D Povey, ... arXiv preprint arXiv:2106.06909, 2021 513(2021)
-
AudioGPT:理解与生成语音、音乐、音效和说话人头部(https://scholar.google.com/citations?view_op=view_citation&hl=en&user=U5xRA6QAAAAJ&citation_for_view=U5xRA6QAAAAJ:QaLwMs-zPFMC) R Huang, M Li, D Yang, J Shi, X Chang, Z Ye, Y Wu, Z Hong, J Huang, ... Proceedings of the AAAI Conference on Artificial Intelligence 38 (21), 23802..., 2024 495(2024)
-
鲁棒语音识别中的环境、麦克风与数据模拟失配分析(https://scholar.google.com/citations?view_op=view_citation&hl=en&user=U5xRA6QAAAAJ&citation_for_view=U5xRA6QAAAAJ:DGpvO1n63MYC) E Vincent, S Watanabe, AA Nugraha, J Barker, R Marxer Computer Speech & Language 46, 535-557, 2017 488(2017)
-
基于单通道掩码预测网络的改进 MVDR 波束成形(https://scholar.google.com/citations?view_op=view_citation&hl=en&user=U5xRA6QAAAAJ&citation_for_view=U5xRA6QAAAAJ:o4Qvs5Y5TLQC) H Erdogan, JR Hershey, S Watanabe, MI Mandel, JL Roux Proc. Interspeech 2016, 1981-1985, 2016 443(2016)
-
基于无排列目标的端到端神经说话人分割聚类(https://scholar.google.com/citations?view_op=view_citation&hl=en&user=U5xRA6QAAAAJ&citation_for_view=U5xRA6QAAAAJ:CzVmvSWNoUEC) Y Fujita, N Kanda, S Horiguchi, K Nagamatsu, S Watanabe arXiv preprint arXiv:1909.05952, 2019 426(2019)
相似文章
@yoheinakajima: 哦,这很酷,我不是pliny,但在GitHub星标中排名第630位!对于VC来说还不错
一位风险投资人庆祝在GitHub星标中排名第630位,受到@elder_plinius的启发,后者通过AI辅助获得了10万星标,并进入GitHub前100名。
@yoheinakajima:我的第一篇SSRN论文 :) https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7147798…
Yohei Nakajima宣布了他的第一篇SSRN论文,并分享了链接。
@ClementDelangue:最近Nvidia(美国开源AI之王)做了很多出色的工作!——跨越了1,000个公共仓库……
Nvidia在Hugging Face上突破了1,000个公共仓库,展示了热门模型,并宣布了Cosmos 3、Alphamayo 2 Super、Nemotron 3/4的计划以及采用OpenMDW框架,凸显了其在开源AI领域的领导地位。
@JeffDean:我的@Google同事@NormJouppi、Sridhar Lakshmanamurthy、Cliff Young和David Patterson最近撰写了一篇论文,该论文…
Google研究人员发表了一篇论文,总结了从TPU v2到Ironwood的TPU超级计算机的演进,详细介绍了架构稳定性、规模、弹性、能效以及八年间3600倍的性能提升。
谷歌的智能体同行评审系统在ICML/STOC处理了约1万篇论文——正式研究论文现已发布 [R]
谷歌在ICML和STOC会议上部署了一个智能体AI同行评审系统,以30分钟周转时间评审了约1万篇论文。正式论文显示,与零样本提示相比,它多发现了34%的数学错误,为大规模AI自动化科学评审树立了先例。