Speaker adaptation of hybrid NN/HMM model for speech recognition based on singular value decomposition

Proceedings of the 9th International Symposium on Chinese Spoken Language Processing, ISCSLP 2014

Volumn , Issue , 2014, Pages 1-5

  Xue, Shaofei ^a   Jiang, Hui ^b   Dai, Lirong ^a  

^a University of Science and Technology of China   (China)

^b YORK UNIVERSITY   (Canada)

Author keywords

Deep Neural Network (DNN); Hybrid DNN HMM; singular value decomposition (SVD); Speaker Adaptation

Indexed keywords

CONTINUOUS SPEECH RECOGNITION; DEEP NEURAL NETWORKS; ELECTRIC SWITCHBOARDS; NEURAL NETWORKS; SPEECH; VOCABULARY CONTROL;

ADAPTATION METHODS; DIAGONAL MATRICES; HYBRID DNN/HMM; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; LARGE VOCABULARY SPEECH RECOGNITION; OVER FITTING PROBLEM; RECOGNITION MODELS; SPEAKER ADAPTATION;

SINGULAR VALUE DECOMPOSITION;

EID: 84912109599     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ISCSLP.2014.6936583     Document Type: Conference Paper

References (29)

1. J. L. Gauvain and Chin-Hui Lee, "Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains," IEEE Transactions on Speech and audio processing, vol. 2, no. 2, pp. 291-298, 1994.
2. S. M. Ahadi and P. C. Woodland, "Combined Bayesian and predictive techniques for rapid speaker adaptation of continuous density hidden Markov models," Computer speech & language, vol. 11, no. 3, pp. 187-206, 1997.
3. Christopher Leggetter and P. C.Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models," Computer Speech & Language, vol. 9, no. 2, pp. 171-185, 1995.
4. Mark J. F. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition," Computer speech & language, vol. 12, no. 2, pp. 75-98, 1998.
5. Vassilios V Digalakis, Dimitry Rtischev, and Leonardo G Neumeyer, "Speaker adaptation using constrained estimation of Gaussian mixtures," IEEE Transactions on Speech and Audio Processing, vol. 3, no. 5, pp. 357-366, 1995.
6. Li Lee and Richard C Rose, "Speaker normalization using efficient frequency warping procedures," in IEEE International Conference of Acoustics,Speech and Signal Processing (ICASSP). IEEE, 1996, vol. 1, pp. 353-356.
7. Hui Jiang, Frank Soong, and Chin-Hui Lee, "Hierarchical stochastic feature matching for robust speech recognition," in IEEE International Conference of Acoustics,Speech and Signal Processing (ICASSP). IEEE, 2001, vol. 1, pp. 217-220.
8. Joao Neto, Lus Almeida, Mike Hochberg, Ciro Martins, Lus Nunes, Steve Renals, and Tony Robinson, "Speaker-adaptation for hybrid HMM-ANN continuous speech recognition system," in EUROSPEECH, 1995.
9. Roberto Gemello, Franco Mana, Stefano Scanzio, Pietro Laface, and Renato De Mori, "Linear hidden transformations for adaptation of hybrid ANN/HMM models," Speech Communication, vol. 49, no. 10, pp. 827-835, 2007.
10. Jan Stadermann and Gerhard Rigoll, "Two-stage speaker adaptation of hybrid tied-posterior acoustic models," in IEEE International Conference of Acoustics,Speech and Signal Processing (ICASSP), 2005.
11. Sabato Marco Siniscalchi, Jinyu Li, and C-H Lee, "Hermitian polynomial for speaker adaptation of connectionist speech recognition systems," IEEE Transactions on Audio, Speech, and Language Processing, vol. 21, no. 10, pp. 2152-2161, 2013.
12. Frank Seide, Gang Li, Xie Chen, and Dong Yu, "Feature engineering in context-dependent deep neural networks for conversational speech transcription," in 2011 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 2011.
13. 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 Spoken Language Technology Workshop (SLT). IEEE, 2012, pp. 366-369.
14. 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 IEEE International Conference of Acoustics,Speech and Signal Processing (ICASSP). IEEE, 2013, pp. 7893-7897.
15. Y.Q Wang and M.J.F Gales, "Tandem system adaptation using multiple linear feature transforms," in IEEE International Conference of Acoustics,Speech and Signal Processing (ICASSP). IEEE, 2013, pp. 7932-7936.
16. Zoltan Tuske, Ralf Schluter, and Hermann Ney, "Deep hierarchical bottleneck mrasta features for LVCSR," in IEEE International Conference of Acoustics,Speech and Signal Processing (ICASSP). IEEE, 2013, pp. 6970-6974.
17. 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 IEEE International Conference of Acoustics,Speech and Signal Processing (ICASSP). IEEE, 2013, pp. 7942-7946.
18. Ossama Abdel-Hamid and Hui Jiang, "Rapid and effective speaker adaptation of convolutional neural network based models for speech recognition," in INTERSPEECH, 2013.
19. Shaofei Xue, Ossama Abdel-Hamid, Hui Jiang, and Lirong Dai, "Direct adaptation of hybrid DNN/HMM model for fast speaker adaptation in LVCSR based on speaker code," in IEEE International Conference of Acoustics,Speech and Signal Processing (ICASSP), 2014.
20. Shaofei Xue, Ossama Abdel-Hamid, Hui Jiang, and Lirong Dai, "Speaker adaptation of deep neural network based on discriminant codes," submitted to IEEE Transactions on Acoustics, Speech and Signal Processing, Feb 2014.
21. Jian Xue, Jinyu Li, Dong Yu, Mike Seltzer, and Yifan Gong, "Singular value decomposition based low-footprint speaker adaptation and personalization for deep neural network," in IEEE International Conference of Acoustics,Speech and Signal Processing (ICASSP), 2014.
22. Misha Denil, Babak Shakibi, Laurent Dinh, Nando de Freitas, et al., "Predicting parameters in deep learning," in Advances in Neural Information Processing Systems, 2013, pp. 2148-2156.
23. Tara N Sainath, Brian Kingsbury, Vikas Sindhwani, Ebru Arisoy, and Bhuvana Ramabhadran, "Low-rank matrix factorization for deep neural network training with high-dimensional output targets," in IEEE International Conference of Acoustics,Speech and Signal Processing (ICASSP). IEEE, 2013, pp. 6655-6659.
24. Jian Xue, Jinyu Li, and Yifan Gong, "Restructuring of deep neural network acoustic models with singular value decomposition," in INTERSPEECH, 2013.
25. K-F Lee and H-W Hon, "Speaker-independent phone recognition using hidden markov models," IEEE Transactions on Acoustics, Speech and Signal Processing, vol. 37, no. 11, pp. 1641-1648, 1989.
26. Jia Pan, Cong Liu, Zhiguo Wang, Yu Hu, and Hui Jiang, "Investigation of deep neural networks (DNN) for large vocabulary continuous speech recognition: Why DNN surpasses GMMs in acoustic modeling," in 8th International Symposium on Chinese Spoken Language Processing (ISCSLP), 2012, pp. 301-305.
27. Yebo Bao, Hui Jiang, Cong Liu, Yu Hu, and Lirong Dai, "Investigation on dimensionality reduction of concatenated features with deep neural network for LVCSR systems," in IEEE 11th International Conference on Signal Processing (ICSP), 2012, vol. 1, pp. 562-566.
28. Yebo Bao, Hui Jiang, Lirong Dai, and Cong Liu, "Incoherent training of deep neural networks to de-correlate bottleneck features for speech recognition," in IEEE International Conference of Acoustics,Speech and Signal Processing (ICASSP), 2013.
29. Shiliang Zhang, Yebo Bao, Pan Zhou, Hui Jiang, and Lirong Dai, "Improving deep neural networks for LVCSR using dropout and shrinking structure," in IEEE International Conference of Acoustics, Speech and Signal Processing (ICASSP), 2014.