Zobrazeno 1 - 6
of 6
pro vyhledávání: '"James Qin"'
Autor:
Yu Zhang, Daniel S. Park, Wei Han, James Qin, Anmol Gulati, Joel Shor, Aren Jansen, Yuanzhong Xu, Yanping Huang, Shibo Wang, Zongwei Zhou, Bo Li, Min Ma, William Chan, Jiahui Yu, Yongqiang Wang, Liangliang Cao, Khe Chai Sim, Bhuvana Ramabhadran, Tara N. Sainath, Francoise Beaufays, Zhifeng Chen, Quoc V. Le, Chung-Cheng Chiu, Ruoming Pang, Yonghui Wu
We summarize the results of a host of efforts using giant automatic speech recognition (ASR) models pre-trained using large, diverse unlabeled datasets containing approximately a million hours of audio. We find that the combination of pre-training, s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7dea4e39aabfa465900cf742628eef2c
http://arxiv.org/abs/2109.13226
http://arxiv.org/abs/2109.13226
Autor:
Anmol Gulati, James Qin, Yonghui Wu, Yanzhang He, Yu Zhang, Tara N. Sainath, Trevor Strohman, Ruoming Pang, Arun Narayanan, Qiao Liang, Shuo-Yiin Chang, Chung-Cheng Chiu, Wei Han, Jiahui Yu, Bo Li
Publikováno v:
ICASSP
End-to-end (E2E) models have shown to outperform state-of-the-art conventional models for streaming speech recognition [1] across many dimensions, including quality (as measured by word error rate (WER)) and endpointer latency [2]. However, the model
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::79f2c3f759db2f52ddb94da74741686d
https://doi.org/10.1109/icassp39728.2021.9413899
https://doi.org/10.1109/icassp39728.2021.9413899
Publikováno v:
INTERSPEECH
Recent advances of end-to-end models have outperformed conventional models through employing a two-pass model. The two-pass model provides better speed-quality trade-offs for on-device speech recognition, where a 1st-pass model generates hypotheses i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7f77b4c1fbbb782983dd6a03d2a71d03
https://doi.org/10.21437/interspeech.2020-2875
https://doi.org/10.21437/interspeech.2020-2875
Autor:
Chung-Cheng Chiu, Ruoming Pang, Anmol Gulati, Wei Han, Zhengdong Zhang, Yonghui Wu, Yu Zhang, Jiahui Yu, James Qin
Publikováno v:
INTERSPEECH
Convolutional neural networks (CNN) have shown promising results for end-to-end speech recognition, albeit still behind other state-of-the-art methods in performance. In this paper, we study how to bridge this gap and go beyond with a novel CNN-RNN-t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9849a524b399977c9fba7e646a160ae8
https://doi.org/10.21437/interspeech.2020-2059
https://doi.org/10.21437/interspeech.2020-2059
Autor:
Niki Parmar, James Qin, Ruoming Pang, Zhengdong Zhang, Yu Zhang, Chung-Cheng Chiu, Anmol Gulati, Yonghui Wu, Jiahui Yu, Shibo Wang, Wei Han
Publikováno v:
INTERSPEECH
Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs). Transformer models are good at capturing content-based global i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e5e747a2aca22bd59991b14ed380e109
Publikováno v:
Methods (San Diego, Calif.). 59(1)
MicroRNAs (miRNAs) are endogenous, non-coding RNAs comprising approximately 21–23 nucleotides that regulate gene expression by binding to and targeting messenger RNA (mRNA) for translational repression or degradation. miRNAs have been shown to regu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::040475b9e1514444b24e712d7b60b351
https://pubmed.ncbi.nlm.nih.gov/23036327
https://pubmed.ncbi.nlm.nih.gov/23036327