Speaker-aware training of LSTM-RNNS for acoustic modelling

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 2016-May, Issue , 2016, Pages 5280-5284

  Tan, Tian ^a   Qian, Yanmin ^a,b   Yu, Dong ^c   Kundu, Souvik ^d   Lu, Liang ^e   Sim, Khe Chai ^d   Xiao, Xiong ^f   Zhang, Yu ^g  

^a SHANGHAI JIAO TONG UNIVERSITY   (China)

^b UNIVERSITY OF CAMBRIDGE   (United Kingdom)

^c MICROSOFT RESEARCH   (United States)

^d NATIONAL UNIVERSITY OF SINGAPORE   (Singapore)

^e UNIVERSITY OF EDINBURGH   (United Kingdom)

^f NANYANG TECHNOLOGICAL UNIVERSITY   (Singapore)

^g MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

i vector; LSTM RNNs; speaker adaptation; speaker aware training; speaking rate

Indexed keywords

EID: 84973380342     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2016.7472685     Document Type: Conference Paper

References (31)

1. Herve A Bourlard and Nelson Morgan, Connectionist speech recognition: a hybrid approach, vol. 247, Springer Science & Business Media, 2012.
2. Geoffrey Hinton, Li Deng, Dong Yu, George E Dahl, Abdelrahman Mohamed, Navdeep Jaitly, Andrew Senior, Vincent Vanhoucke, Patrick Nguyen, Tara N Sainath, et al., "Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups, " Signal Processing Magazine, IEEE, vol. 29, no. 6, pp. 82-97, 2012.
3. Yoshua Bengio, Patrice Simard, and Paolo Frasconi, "Learning long-term dependencies with gradient descent is difficult, " Neural Networks, IEEE Transactions on, vol. 5, no. 2, pp. 157-166, 1994.
4. Sepp Hochreiter and Jürgen Schmidhuber, "Long short-term memory, " Neural computation, vol. 9, no. 8, pp. 1735-1780, 1997.
5. Hasim Sak, Andrew Senior, and Françoise Beaufays, "Long short-term memory recurrent neural network architectures for large scale acoustic modeling, " in INTERSPEECH, 2014.
6. Xiangang Li and Xihong Wu, "Constructing long short-term memory based deep recurrent neural networks for large vocabulary speech recognition, " in ICASSP. IEEE, 2015, pp. 4520-4524.
7. Yan Huang, Dong Yu, Chaojun Liu, and Yifan Gong, "A comparative analytic study on the Gaussian mixture and context dependent deep neural network hidden Markov models, " in INTERSPEECH, 2014.
8. Yu Dong and Deng Li, Automatic speech recognition, A deep learning approach, Springer.
9. Frank Seide, Gang Li, Xie Chen, and Dong Yu, "Feature engineering in context-dependent deep neural networks for conversational speech transcription, " in ASRU. IEEE, 2011, pp. 24-29.
10. Kaisheng Yao, Dong Yu, Frank Seide, Hang Su, Li Deng, and Yifan Gong, "Adaptation of context-dependent deep neural networks for automatic speech recognition., " in SLT, 2012, pp. 366-369.
11. Dong Yu, Kaisheng Yao, Hang Su, Gang Li, and Frank Seide, "Kl-divergence regularized deep neural network adaptation for improved large vocabulary speech recognition, " in ICASSP. IEEE, 2013, pp. 7893-7897.
12. Ossama Abdel-Hamid and Hui Jiang, "Fast speaker adaptation of hybrid nn/hmm model for speech recognition based on discriminative learning of speaker code, " in ICASSP. IEEE, 2013, pp. 7942-7946.
13. George Saon, Hagen Soltau, David Nahamoo, and Michael Picheny, "Speaker adaptation of neural network acoustic models using i-vectors, " in ASRU. IEEE, 2013, pp. 55-59.
14. Romain Serizel and Diego Giuliani, "Vocal tract length normalisation approaches to dnn-based children's and adults' speech recognition, " in Spoken Language Technology Workshop (SLT), 2014 IEEE. IEEE, 2014, pp. 135-140.
15. Yajie Miao and Florian Metze, "On speaker adaptation of long short-term memory recurrent neural networks, " in INTERSPEECH, 2015.
16. Najim Dehak, Patrick Kenny, Réda Dehak, Pierre Dumouchel, and Pierre Ouellet, "Front-end factor analysis for speaker verification, " Audio, Speech, and Language Processing, IEEE Transactions on, vol. 19, no. 4, pp. 788-798, 2011.
17. Hengguan Huang and Khe Chai Sim, "An investigation of augmenting speaker representations to improve speaker normalisation for dnn-based speech recognition, " in ICASSP. IEEE, 2015, pp. 4610-4613.
18. Xie Chen, Tian Tan, Xunying Liu, Pierre Lanchantin, Moquan Wan, Mark Gales, and PhilWoodland, "Recurrent neural network language model adaptation for multi-genre broadcast speech recognition, " in INTERSPEECH, 2015.
19. Tomas Mikolov and Geoffrey Zweig, "Context dependent recurrent neural network language model., " in SLT, 2012, pp. 234-239.
20. Yajie Miao, Hao Zhang, and Florian Metze, "Towards speaker adaptive training of deep neural network acoustic models, " in INTERSPEECH, 2014.
21. Yun Lei, Nicolas Scheffer, Luciana Ferrer, and Moray McLaren, "A novel scheme for speaker recognition using a phonetically-aware deep neural network, " in ICASSP. IEEE, 2014, pp. 1695-1699.
22. Dongpeng Chen, Brian Mak, Cheung-Chi Leung, and Sunil Sivadas, "Joint acoustic modeling of triphones and trigraphemes by multi-task learning deep neural networks for low-resource speech recognition, " in ICASSP. IEEE, 2014, pp. 5592-5596.
23. Nanxin Chen, Yanmin Qian, and Kai Yu, "Multi-task learning for text-dependent speaker verification, " in INTERSPEECH, 2015.
24. Matthew Siegler, Richard M Stern, et al., "On the effects of speech rate in large vocabulary speech recognition systems, " in ICASSP. IEEE, 1995, vol. 1, pp. 612-615.
25. Nelson Morgan, Eric Fosler-Lussier, and Nikki Mirghafori, "Speech recognition using on-line estimation of speaking rate., " in Eurospeech, 1997, vol. 97, pp. 2079-2082.
26. Stephen M Chu and Daniel Povey, "Speaking rate adaptation using continuous frame rate normalization, " in ICASSP. IEEE, 2010, pp. 4306-4309.
27. Xiangyu Zeng, Shi Yin, and Dong Wang, "Learning speech rate in speech recognition, " in INTERSPEECH, 2015, pp. 528-532.
28. Thomas Hain, Luká Burget, John Dines, Philip N Garner, Frantisek Grézl, Asmaa El Hannani, Marijn Huijbregts, Martin Karafiat, Mike Lincoln, and VincentWan, "Transcribing meetings with the amida systems, " Audio, Speech, and Language Processing, IEEE Transactions on, vol. 20, no. 2, pp. 486-498, 2012.
29. Pawel Swietojanski, Arnab Ghoshal, and Steve Renals, "Hybrid acoustic models for distant and multichannel large vocabulary speech recognition, " in ASRU. IEEE, 2013, pp. 285-290.
30. Daniel Povey, Arnab Ghoshal, Gilles Boulianne, Lukás Burget, Ondrej Glembek, Nagendra Goel, Mirko Hannemann, Petr Motlícek, Yanmin Qian, Petr Schwarz, et al., "The kaldi speech recognition toolkit, " 2011.
31. Dong Yu, Adam Eversole, Mike Seltzer, Kaisheng Yao, Zhiheng Huang, Brian Guenter, Oleksii Kuchaiev, Yu Zhang, Frank Seide, Huaming Wang, et al., "An introduction to computational networks and the computational network toolkit, " Tech. Rep., Microsoft Research, 2014.