Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Trevor Strohman"'
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4e20c0aa207da2c3be5520bd64c877e9
https://doi.org/10.1109/icassp49357.2023.10095204
https://doi.org/10.1109/icassp49357.2023.10095204
Publikováno v:
2022 IEEE Spoken Language Technology Workshop (SLT).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::36fe90e2f7cd03f8239bd71b2cbc5595
https://doi.org/10.1109/slt54892.2023.10023016
https://doi.org/10.1109/slt54892.2023.10023016
Publikováno v:
2022 IEEE Spoken Language Technology Workshop (SLT).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6ae0ceca257d1295e060e2d6d5f13f49
https://doi.org/10.1109/slt54892.2023.10022938
https://doi.org/10.1109/slt54892.2023.10022938
Publikováno v:
2022 IEEE Spoken Language Technology Workshop (SLT).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e0e0aaaf8d8171154f40e7cc36d2b7c4
https://doi.org/10.1109/slt54892.2023.10023346
https://doi.org/10.1109/slt54892.2023.10023346
Autor:
Chao-Han Huck Yang, Bo Li, Yu Zhang, Nanxin Chen, Rohit Prabhavalkar, Tara N. Sainath, Trevor Strohman
In this work, we propose a new parameter-efficient learning framework based on neural model reprogramming for cross-lingual speech recognition, which can \textbf{re-purpose} well-trained English automatic speech recognition (ASR) models to recognize
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a8cfe93225053687c4487ed2d5a0904b
Autor:
Zhong Meng, Tongzhou Chen, Rohit Prabhavalkar, Yu Zhang, Gary Wang, Kartik Audhkhasi, Jesse Emond, Trevor Strohman, Bhuvana Ramabhadran, W. Ronny Huang, Ehsan Variani, Yinghui Huang, Pedro J. Moreno
Text-only adaptation of a transducer model remains challenging for end-to-end speech recognition since the transducer has no clearly separated acoustic model (AM), language model (LM) or blank model. In this work, we propose a modular hybrid autoregr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d7dcdb301bc7244abe1eef7c4a80c217
http://arxiv.org/abs/2210.17049
http://arxiv.org/abs/2210.17049
Autor:
Zhouyuan Huo, Dongseong Hwang, Khe Chai Sim, Shefali Garg, Ananya Misra, Nikhil Siddhartha, Trevor Strohman, Francoise Beaufays
Publikováno v:
Interspeech 2022.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fd44d65b7052c2ea3c0787b3fa218bdc
https://doi.org/10.21437/interspeech.2022-10904
https://doi.org/10.21437/interspeech.2022-10904
Autor:
Ke Hu, Tara Sainath, Yanzhang He, Rohit Prabhavalkar, Trevor Strohman, Sepand Mavandadi, Weiran Wang
Publikováno v:
Interspeech 2022.
Text-only and semi-supervised training based on audio-only data has gained popularity recently due to the wide availability of unlabeled text and speech data. In this work, we propose incorporating text-only and semi-supervised training into an atten
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::751348309b503b2c02ece097430d1438
https://doi.org/10.21437/interspeech.2022-243
https://doi.org/10.21437/interspeech.2022-243
Autor:
Bo Li, Tara Sainath, Ruoming Pang, Shuo-Yiin Chang, Qiumin Xu, Trevor Strohman, Vince Chen, Qiao Liang, Heguang Liu, Yanzhang He, Parisa Haghani, Sameer Bidichandani
On-device end-to-end (E2E) models have shown improvements over a conventional model on English Voice Search tasks in both quality and latency. E2E models have also shown promising results for multilingual automatic speech recognition (ASR). In this p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e69d8dfd3d8f4389b06eed47e083c02c
http://arxiv.org/abs/2208.13916
http://arxiv.org/abs/2208.13916
Autor:
Shuo-Yiin Chang, Guru Prakash, Zelin Wu, Tara Sainath, Bo Li, Qiao Liang, Adam Stambler, Shyam Upadhyay, Manaal Faruqui, Trevor Strohman
In voice-enabled applications, a predetermined hotword isusually used to activate a device in order to attend to the query.However, speaking queries followed by a hotword each timeintroduces a cognitive burden in continued conversations. Toavoid repe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::50678679e5680829604b4b3647342512
http://arxiv.org/abs/2208.13322
http://arxiv.org/abs/2208.13322