Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Jesse Emond"'
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:
Bhuvana Ramabhadran, Mohammadreza Ghodsi, Yinghui Huang, Heiga Zen, Pedro J. Moreno, Yu Zhang, Zhehuai Chen, Andrew Rosenberg, Jesse Emond, Gary Wang
Publikováno v:
Interspeech 2021.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::639f62ef951e3dc2ecbd0f0424990587
https://doi.org/10.21437/interspeech.2021-677
https://doi.org/10.21437/interspeech.2021-677
Publikováno v:
Interspeech 2021.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::060397afb42f4058b31cc8d68c5da23b
https://doi.org/10.21437/interspeech.2021-648
https://doi.org/10.21437/interspeech.2021-648
Publikováno v:
ICASSP
Multilingual Automated Speech Recognition (ASR) systems allow for the joint training of data-rich and data-scarce languages in a single model. This enables data and parameter sharing across languages, which is especially beneficial for the data-scarc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6a151204da3e0d461f9892fc4c305984
http://arxiv.org/abs/2004.09571
http://arxiv.org/abs/2004.09571
Publikováno v:
ICASSP
Code-switching occurs when the speaker alternates between two or more languages or dialects. It is a pervasive phenomenon in most Indic spoken languages. Code-switching poses a challenge in language modeling as it complicates the orthographic realiza
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6975ffa69affa2c16a54150b09ac1b4c
https://doi.org/10.1109/icassp.2019.8682824
https://doi.org/10.1109/icassp.2019.8682824