| Google usm: Scaling automatic speech recognition beyond 100 languages Y Zhang, W Han, J Qin, Y Wang, A Bapna, Z Chen, N Chen, B Li, ... arXiv preprint arXiv:2303.01037, 2023 | 298 | 2023 |
| A streaming on-device end-to-end model surpassing server-side conventional model quality and latency TN Sainath, Y He, B Li, A Narayanan, R Pang, A Bruguier, S Chang, W Li, ... ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 236 | 2020 |
| An unsupervised approach to cochannel speech separation K Hu, D Wang IEEE Transactions on Audio, Speech, and Language Processing 21, 122-131, 2013 | 124 | 2013 |
| Deliberation model based two-pass end-to-end speech recognition K Hu, TN Sainath, R Pang, R Prabhavalkar ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 97 | 2020 |
| A tandem algorithm for singing pitch extraction and voice separation from music accompaniment CL Hsu, DL Wang, JSR Jang, K Hu IEEE Transactions on audio, speech, and language processing 20 (5), 1482-1491, 2012 | 95 | 2012 |
| Unvoiced speech segregation from nonspeech interference via CASA and spectral subtraction K Hu, DL Wang IEEE Transactions on Audio, Speech, and Language Processing 19 (6), 1600-1609, 2010 | 68 | 2010 |
| Transformer Based Deliberation for Two-Pass Speech Recognition K Hu, R Pang, TN Sainath, T Strohman 2021 IEEE Spoken Language Technology Workshop (SLT), 68-74, 2021 | 42 | 2021 |
| Learning word-level confidence for subword end-to-end automatic speech recognition D Qiu, Q Li, Y He, Y Zhang, B Li, L Cao, R Prabhavalkar, D Bhatia, W Li, ... US Patent 11,610,586, 2023 | 32 | 2023 |
| Learning word-level confidence for subword end-to-end ASR D Qiu, Q Li, Y He, Y Zhang, B Li, L Cao, R Prabhavalkar, D Bhatia, W Li, ... ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021 | 31 | 2021 |
| An iterative model-based approach to cochannel speech separation K Hu, DL Wang EURASIP Journal on Audio, Speech, and Music Processing 2013, 1-11, 2013 | 29 | 2013 |
| Phoneme-Based Contextualization for Cross-Lingual Speech Recognition in End-to-End Models K Hu, A Bruguier, TN Sainath, R Prabhavalkar, G Pundak Proc. Interspeech 2019, 2155--2159, 2019 | 22 | 2019 |
| Deliberation of streaming rnn-transducer by non-autoregressive decoding W Wang, K Hu, TN Sainath ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022 | 20 | 2022 |
| Massively multilingual shallow fusion with large language models K Hu, TN Sainath, B Li, N Du, Y Huang, AM Dai, Y Zhang, R Cabrera, ... ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023 | 16 | 2023 |
| Mixture-of-expert conformer for streaming multilingual asr K Hu, B Li, TN Sainath, Y Zhang, F Beaufays arXiv preprint arXiv:2305.15663, 2023 | 15 | 2023 |
| A Time-Frequency Analysis Based Blind Source Deconvolution Method K Hu, Z Wang Chinese Journal of Electronics 34 (007), 1246-1254, 2006 | 13* | 2006 |
| Improving deliberation by text-only and semi-supervised training K Hu, TN Sainath, Y He, R Prabhavalkar, T Strohman, S Mavandadi, ... Interspeech 2022, 2022 | 12 | 2022 |
| Incorporating spectral subtraction and noise type for unvoiced speech segregation K Hu, DL Wang 2009 IEEE International Conference on Acoustics, Speech and Signal …, 2009 | 9 | 2009 |
| Scaling up deliberation for multilingual ASR K Hu, B Li, TN Sainath 2022 IEEE Spoken Language Technology Workshop (SLT), 771-776, 2023 | 8 | 2023 |
| Phoneme-based contextualization for cross-lingual speech recognition in end-to-end models K Hu, AJ Bruguier, TN Sainath, RP Prabhavalkar, G Pundak US Patent 11,270,687, 2022 | 8 | 2022 |
| A Deliberation-based Joint Acoustic and Text Decoder S Mavandadi, TN Sainath, K Hu, Z Wu Proc. Interspeech 2021, 2057-2061, 2021 | 8 | 2021 |
Tara SainathDistinguished Research Scientist, Google Deep MindVerified email at google.com
