Volgen
Chunxi Liu
Chunxi Liu
Two Sigma
Geverifieerd e-mailadres voor twosigma.com
Titel
Geciteerd door
Geciteerd door
Jaar
Transformer-based acoustic modeling for hybrid speech recognition
Y Wang, A Mohamed, D Le, C Liu, A Xiao, J Mahadeokar, H Huang, ...
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
1852020
A keyword search system using open source software
J Trmal, G Chen, D Povey, S Khudanpur, P Ghahremani, X Zhang, ...
2014 IEEE Spoken Language Technology Workshop (SLT), 530-535, 2014
522014
ASR for under-resourced languages from probabilistic transcription
MA Hasegawa-Johnson, P Jyothi, D McCloy, M Mirbagheri, GM Di Liberto, ...
IEEE/ACM Transactions on Audio, Speech, and Language Processing 25 (1), 50-63, 2016
372016
Deja-vu: Double feature presentation and iterated loss in deep transformer networks
A Tjandra, C Liu, F Zhang, X Zhang, Y Wang, G Synnaeve, S Nakamura, ...
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
322020
Deep contextual language understanding in spoken dialogue systems
C Liu, P Xu, R Sarikaya
Sixteenth annual conference of the international speech communication …, 2015
322015
Adapting ASR for under-resourced languages using mismatched transcriptions
C Liu, P Jyothi, H Tang, V Manohar, R Sloan, T Kekona, ...
2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016
302016
Improving RNN transducer based ASR with auxiliary tasks
C Liu, F Zhang, D Le, S Kim, Y Saraf, G Zweig
2021 IEEE Spoken Language Technology Workshop (SLT), 172-179, 2021
282021
Dual application of speech enhancement for automatic speech recognition
A Pandey, C Liu, Y Wang, Y Saraf
2021 IEEE Spoken Language Technology Workshop (SLT), 223-228, 2021
212021
Faster, simpler and more accurate hybrid asr systems using wordpieces
F Zhang, Y Wang, X Zhang, C Liu, Y Saraf, G Zweig
arXiv preprint arXiv:2005.09150, 2020
212020
Multilingual graphemic hybrid ASR with massive data augmentation
C Liu, Q Zhang, X Zhang, K Singh, Y Saraf, G Zweig
arXiv preprint arXiv:1909.06522, 2019
212019
Topic Identification for Speech without ASR
C Liu, J Trmal, M Wiesner, C Harman, S Khudanpur
INTERSPEECH, 2017
172017
Benchmarking lf-mmi, ctc and rnn-t criteria for streaming asr
X Zhang, F Zhang, C Liu, K Schubert, J Chan, P Prakash, J Liu, CF Yeh, ...
2021 IEEE spoken language technology workshop (SLT), 46-51, 2021
162021
Low-resource open vocabulary keyword search using point process models
C Liu, A Jansen, G Chen, K Kintzley, J Trmal, S Khudanpur
Fifteenth Annual Conference of the International Speech Communication …, 2014
162014
An empirical evaluation of zero resource acoustic unit discovery
C Liu, J Yang, M Sun, S Kesiraju, A Rott, L Ondel, P Ghahremani, ...
IEEE ICASSP, 2017
152017
Contextualizing ASR lattice rescoring with hybrid pointer network language model
DR Liu, C Liu, F Zhang, G Synnaeve, Y Saraf, G Zweig
arXiv preprint arXiv:2005.07394, 2020
142020
Automatic speech recognition and topic identification for almost-zero-resource languages
M Wiesner, C Liu, L Ondel, C Harman, V Manohar, J Trmal, Z Huang, ...
arXiv preprint arXiv:1802.08731, 2018
102018
Conformer-based self-supervised learning for non-speech audio tasks
S Srivastava, Y Wang, A Tjandra, A Kumar, C Liu, K Singh, Y Saraf
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
92022
Towards measuring fairness in speech recognition: casual conversations dataset transcriptions
C Liu, M Picheny, L Sarı, P Chitkara, A Xiao, X Zhang, M Chou, ...
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
72022
Pretraining by backtranslation for end-to-end asr in low-resource settings
M Wiesner, A Renduchintala, S Watanabe, C Liu, N Dehak, S Khudanpur
arXiv preprint arXiv:1812.03919, 2018
62018
Streaming transformer transducer based speech recognition using non-causal convolution
Y Shi, C Wu, D Wang, A Xiao, J Mahadeokar, X Zhang, C Liu, K Li, ...
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
52022
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–20