Yongqiang Wang
Yongqiang Wang
Research Scientist, Google
Verified email at google.com - Homepage
Title
Cited by
Cited by
Year
An investigation of deep neural networks for noise robust speech recognition
ML Seltzer, D Yu, Y Wang
2013 IEEE international conference on acoustics, speech and signal …, 2013
6442013
Towards end-to-end spoken language understanding
D Serdyuk, Y Wang, C Fuegen, A Kumar, B Liu, Y Bengio
2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018
1122018
Efficient lattice rescoring using recurrent neural network language models
X Liu, Y Wang, X Chen, MJF Gales, PC Woodland
2014 IEEE International Conference on Acoustics, Speech and Signal …, 2014
872014
Adaptation of deep neural network acoustic models using factorised i-vectors
P Karanasou, Y Wang, MJF Gales, PC Woodland
Fifteenth Annual Conference of the International Speech Communication …, 2014
782014
Efficient GPU-based training of recurrent neural network language models using spliced sentence bunch
X Chen, Y Wang, X Liu, MJF Gales, PC Woodland
Fifteenth Annual Conference of the International Speech Communication …, 2014
702014
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
672020
Simplifying long short-term memory acoustic models for fast training and decoding
Y Miao, J Li, Y Wang, SX Zhang, Y Gong
2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016
672016
Speaker and noise factorization for robust speech recognition
Y Wang, MJF Gales
IEEE Transactions on Audio, Speech, and Language Processing 20 (7), 2149-2158, 2012
562012
Transformer-transducer: End-to-end speech recognition with self-attention
CF Yeh, J Mahadeokar, K Kalgaonkar, Y Wang, D Le, M Jain, K Schubert, ...
arXiv preprint arXiv:1910.12977, 2019
432019
Investigations on speaker adaptation of LSTM RNN models for speech recognition
C Liu, Y Wang, K Kumar, Y Gong
2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016
412016
Small-footprint high-performance deep neural network-based speech recognition using split-VQ
Y Wang, J Li, Y Gong
2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015
372015
Speaker and noise factorisation on the AURORA4 task
YQ Wang, MJF Gales
Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International …, 2011
292011
Model-based approaches to handling additive noise in reverberant environments
MJF Gales, YQ Wang
Hands-free Speech Communication and Microphone Arrays (HSCMA), 2011 Joint …, 2011
272011
Sample-separation-margin based minimum classification error training of pattern classifiers with quadratic discriminant functions
Y Wang, Q Huo
Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International …, 2010
202010
Semi-Supervised Training in Deep Learning Acoustic Model.
Y Huang, Y Wang, Y Gong
Interspeech, 3848-3852, 2016
192016
End-to-end contextual speech recognition using class language models and a token passing decoder
Z Chen, M Jain, Y Wang, ML Seltzer, C Fuegen
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
182019
A study of designing compact recognizers of handwritten Chinese characters using multiple-prototype based classifiers
Y Wang, Q Huo
2010 International Conference on Pattern Recognition, 1872-1875, 2010
172010
Building compact recognizers of handwritten Chinese characters using precision constrained Gaussian model, minimum classification error training and parameter compression
Y Wang, Q Huo
International journal on document analysis and recognition 14 (3), 255-262, 2011
152011
Streaming Transformer-based Acoustic Models Using Self-attention with Augmented Memory
C Wu, Y Wang, Y Shi, CF Yeh, F Zhang
arXiv preprint arXiv:2005.08042, 2020
142020
Tandem system adaptation using multiple linear feature transforms
YQ Wang, MJF Gales
2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013
132013
The system can't perform the operation now. Try again later.
Articles 1–20