Unsupervised adaptation for deep neural network using linear least square method

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn 2015-January, Issue , 2015, Pages 2887-2891

  Hsiao, Roger ^a   Ng, Tim ^a   Tsakalidis, Stavros ^a   Nguyen, Long ^a   Schwartz, Richard ^a  

^a BBN TECHNOLOGIES   (United States)

Author keywords

Deep neural network; Keyword search; Unsupervised adaptation

Indexed keywords

SEARCH ENGINES; SPEECH COMMUNICATION; SPEECH RECOGNITION; SURFACE RECONSTRUCTION;

DEEP NEURAL NETWORKS; ENVIRONMENT ADAPTATION; KEYWORD SEARCH; LINEAR LEAST SQUARE METHODS; LOW RESOURCE LANGUAGES; MODEL-BASED OPC; UNSUPERVISED ADAPTATION; WORD ERROR RATE;

LEAST SQUARES APPROXIMATIONS;

EID: 84959141860     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (23)

1. G. Hinton, L. Deng, D. Yu, A. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T. Sainath, G. Dahl, and B. Kingsbury, "Deep Neural Networks for Acoustic Modeling in Speech Recognition, " IEEE Signal Processing Magazine, vol. 29, no. 6, pp. 82-97, 2012.
2. G. Dahl, D. Yu, L. Deng, and A. Acero, "Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition, " IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 1, pp. 30-42, 2012.
3. B. Kingsbury, "Lattice-based Optimization of Sequence Classification Criteria for Neural Network Acoustic Modeling, " in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, 2009.
4. K. Veselý, A. Ghoshal, L. Burget, and D. Povey, "Sequencediscriminative Training of Deep Neural Networks, " in Proceedings of the INTERSPEECH, 2013.
5. M. Karafiát, F. Grézl, M. Hannemann, K. Veselý, and J. H. Cernocký, "BUT BABEL System for Spontaneous Cantonese, " in Proceedings of the INTERSPEECH, 2013.
6. K. Yao, D. Yu, F. Seide, H. Su, L. Deng, and Y. Gong, "Adaptation of Context-dependent Deep Neural Networks for Automatic Speech Recognition, " in IEEE Spoken Language Technology Workshop, 2012, pp. 366-369.
7. H. Liao, "Speaker Adaptation of Context Dependent Deep Neural Networks, " in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, 2013, pp. 7947-7951.
8. D. Yu, K. Yao, H. Su, G. Li, and F. Seide, "KL-Divergence Regularized Deep Neural Network Adaptation For Improved Large Vocabulary Speech Recognition, " in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, 2013.
9. G. Saon, H. Soltau, D. Nahamoo, and M. Picheny, "Speaker Adaptation of Neural Network Acoustic Models Using I-Vectors, " in Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding, 2013.
10. Y. Miao, H. Zhang, and F. Metze, "Towards Speaker Adaptive Training of Deep Neural Network Acoustic Models, " in Proceedings of the INTERSPEECH, 2014.
11. C. Leggetter and P. Woodland, "Maximum Likelihood Linear Regression for Speaker Adaptation of Continuous Density Hidden Markov Models, " Computer Speech and Language, vol. 9, pp. 171-185, 1995.
12. J. Gauvain and C. 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.
13. S. A. Yeung and M. Siu, "Improved Performance of Aurora 4 Using HTK and Unsupervised MLLR Adaptation, " in Proceedings of the International Conference on Spoken Language Processing, 2004, pp. 221-224.
14. T. Schultz and A. Waibel, "Language Independent and Language Adaptive Acoustic Modeling for Speech Recognition, " Speech Communication, vol. 35, no. 1-2, pp. 31-51, 2001.
15. P. Karanasou, Y. Wang, M. Gales, and P. Woodland, "Adaptation of Deep Neural Network Acoustic Models Using Factorised I-Vectors, " in Proceedings of the INTERSPEECH, 2014.
16. E. Castillo, O. Fontenla-Romero, B. Guijarro-Berdiñas, and A. Alonso-Betanzos, "A Global Optimum Approach for Onelayer Neural Networks, " Neural Computation, vol. 14, no. 6, pp. 1429-1449, 2002.
17. D. Yu and L. Deng, "Efficient and Effective Algorithms for Training Single-Hidden-Layer Neural Networks, " Pattern Recognition Letters, vol. 3, no. 5, pp. 554-558, 2012.
18. "OpenKWS13 Keyword Search Evaluation Plan, " http://www. nist. gov/itl/iad/mig/upload/OpenKWS13-EvalPlan. pdf, 2013.
19. R. Hsiao, T. Ng, F. Grézl, D. Karakos, S. Tsakalidis, L. Nguyen, and R. Schwartz, "Discriminative Semi-supervised Training for Keyword Search in Low Resource Languages, " in Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding, 2013.
20. T. Ng, B. Zhang, S. Matsoukas, and L. Nguyen, "Region Dependent Transform on MLP Features for Speech Recognition, " in Proceedings of the INTERSPEECH, 2011.
21. D. Karakos, R. Schwartz, S. Tsakalidis, L. Zhang, S. Ranjan, T. Ng, R. Hsiao, G. Saikumar, I. Bulyko, L. Nguyen, J. Makhoul, F. Grézl, M. Hannemann, M. Karafiát, I. Szoke, K. Veselý, L. Lamel, and V.-B. Le, "Score Normalization and System Combination for Improved Keyword Spotting in Speech, " in Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding, 2013.
22. R. Hsiao, T. Ng, L. Zhang, S. Ranjan, S. Tsakalidis, L. Nguyen, and R. Schwartz, "Improving Semi-supervised Deep Neural Network for Keyword Search in Low Resource Languages, " in Proceedings of the INTERSPEECH, 2014.
23. F. Grézl and M. Karafiát, "Semi-Supervised Bootstrapping Approach for Neural Network Feature Extractor Training, " in Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding, 2013.