Follow
Meng Cai
Meng Cai
Microsoft Research Asia
Verified email at microsoft.com - Homepage
Title
Cited by
Cited by
Year
Maxout neurons for deep convolutional and LSTM neural networks in speech recognition
M Cai, J Liu
Speech Communication 77, 53-64, 2016
1122016
Deep maxout neural networks for speech recognition
M Cai, Y Shi, J Liu
2013 IEEE Workshop on Automatic Speech Recognition and Understanding, 291-296, 2013
932013
Convolutional maxout neural networks for speech separation
L Hui, M Cai, C Guo, L He, WQ Zhang, J Liu
2015 IEEE international symposium on signal processing and information …, 2015
432015
Investigation of bottleneck features and multilingual deep neural networks for speaker verification.
Y Tian, M Cai, L He, J Liu
Interspeech, 1151-1155, 2015
422015
A compact CNN-DBLSTM based character model for offline handwriting recognition with Tucker decomposition
H Ding, K Chen, Y Yuan, M Cai, L Sun, S Liang, Q Huo
2017 14th IAPR international conference on document analysis and recognition …, 2017
392017
Efficient one-pass decoding with NNLM for speech recognition
Y Shi, WQ Zhang, M Cai, J Liu
IEEE Signal Processing Letters 21 (4), 377-381, 2014
312014
Improving end-to-end contextual speech recognition with fine-grained contextual knowledge selection
M Han, L Dong, Z Liang, M Cai, S Zhou, Z Ma, B Xu
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
292022
A compact cnn-dblstm based character model for online handwritten chinese text recognition
K Chen, L Tian, H Ding, M Cai, L Sun, S Liang, Q Huo
2017 14th IAPR international conference on document analysis and Recognition …, 2017
252017
Variance regularization of RNNLM for speech recognition
Y Shi, WQ Zhang, M Cai, J Liu
2014 IEEE International Conference on Acoustics, Speech and Signal …, 2014
242014
Convolutional maxout neural networks for low-resource speech recognition
M Cai, Y Shi, J Kang, J Liu, T Su
The 9th International Symposium on Chinese Spoken Language Processing, 133-137, 2014
192014
Improving rnn transducer modeling for small-footprint keyword spotting
Y Tian, H Yao, M Cai, Y Liu, Z Ma
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
172021
An open vocabulary OCR system with hybrid word-subword language models
M Cai, W Hu, K Chen, L Sun, S Liang, X Mo, Q Huo
2017 14th IAPR International Conference on Document Analysis and Recognition …, 2017
152017
Compact and efficient WFST-based decoders for handwriting recognition
M Cai, Q Huo
2017 14th IAPR International Conference on Document Analysis and Recognition …, 2017
142017
High-performance Swahili keyword search with very limited language pack: The THUEE system for the OpenKWS15 evaluation
M Cai, Z Lv, C Lu, J Kang, L Hui, Z Zhang, J Liu
2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU …, 2015
142015
Stochastic pooling maxout networks for low-resource speech recognition
M Cai, Y Shi, J Liu
2014 IEEE International Conference on Acoustics, Speech and Signal …, 2014
132014
Sequence discriminative training for offline handwriting recognition by an interpolated CTC and lattice-free MMI objective function
W Hu, M Cai, K Chen, H Ding, L Sun, S Liang, X Mo, Q Huo
2017 14th IAPR International Conference on Document Analysis and Recognition …, 2017
122017
Improving rnn transducer with normalized jointer network
M Huang, J Zhang, M Cai, Y Zhang, J Yao, Y You, Y He, Z Ma
arXiv preprint arXiv:2011.01576, 2020
92020
Temporal kernel neural network language model
Y Shi, WQ Zhang, M Cai, J Liu
2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013
92013
Deep neural networks based speaker modeling at different levels of phonetic granularity
Y Tian, L He, M Cai, WQ Zhang, J Liu
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
82017
Neuron sparseness versus connection sparseness in deep neural network for large vocabulary speech recognition
J Kang, C Lu, M Cai, WQ Zhang, J Liu
2015 IEEE international conference on acoustics, speech and signal …, 2015
82015
The system can't perform the operation now. Try again later.
Articles 1–20