On speaker adaptation of long short-term memory recurrent neural networks

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

Volumn 2015-January, Issue , 2015, Pages 1101-1105

  Miao, Yajie ^a   Metze, Florian ^a  

^a Carnegie Mellon University ^*  (United States)

Author keywords

Acoustic modeling; Long short term memory; Recurrent neural network; Speaker adaptation

Indexed keywords

BRAIN; SPEECH COMMUNICATION; SPEECH RECOGNITION;

ACOUSTIC MODEL; ADAPTATION TECHNIQUES; BENCHMARK DATASETS; LONG SHORT TERM MEMORY; RECURRENT NEURAL NETWORK (RNN); SPEAKER ADAPTATION; SPEAKER DEPENDENTS; TEMPORAL DYNAMICS;

RECURRENT NEURAL NETWORKS;

EID: 84938725974     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (34)

1. G. E. Dahl, D. Yu, L. Deng, and A. Acero, "Context-dependentpre-trained deep neural networks for large-vocabulary speechrecognition, " Audio, Speech, and Language Processing, IEEETransactions on, vol. 20, no. 1, pp. 30-42, 2012.
2. G. Hinton, L. Deng, D. Yu, G. E. Dahl, A.-r. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T. N. Sainath et al., "Deepneural networks for acoustic modeling in speech recognition: Theshared views of four research groups, " Signal Processing Magazine, IEEE, vol. 29, no. 6, pp. 82-97, 2012.
3. Y. Miao, F. Metze, and S. Rawat, "Deep maxout networks for lowresourcespeech recognition, " in Automatic Speech Recognitionand Understand ing (ASRU), 2013 IEEE Workshop on. IEEE, 2013, pp. 398-403.
4. T. N. Sainath, A.-r. Mohamed, B. Kingsbury, and B. Ramabhadran, "Deep convolutional neural networks for lvcsr, " in Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE InternationalConference on. IEEE, 2013, pp. 8614-8618.
5. O. Abdel-Hamid, A.-R. Mohamed, H. Jiang, L. Deng, G. Penn, and D. Yu, "Convolutional neural networks for speech recognition, "IEEE/ACM Transactions on Audio, Speech and LanguageProcessing (TASLP), vol. 22, no. 10, pp. 1533-1545, 2014.
6. Y. Miao and F. Metze, "Improving language-universal feature extractionwith deep maxout and convolutional neural networks, " inFifteenth Annual Conference of the International Speech CommunicationAssociation (INTERSPEECH). ISCA, 2014.
7. H. Soltau, G. Saon, and T. N. Sainath, "Joint training of convolutionaland non-convolutional neural networks, " in Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE InternationalConference on. IEEE, 2014, pp. 5572-5576.
8. A. Graves, A.-R. Mohamed, and G. Hinton, "Speech recognitionwith deep recurrent neural networks, " in Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conferenceon. IEEE, 2013, pp. 6645-6649.
9. A. L. Maas, Q. V. Le, T. M. O'Neil, O. Vinyals, P. Nguyen, and A. Y. Ng, "Recurrent neural networks for noise reduction in robustasr, " in Thirteenth Annual Conference of the International SpeechCommunication Association (INTERSPEECH). ISCA, 2012.
10. Y. Bengio, P. Simard, and P. Frasconi, "Learning long-term dependencieswith gradient descent is difficult, " Neural Networks, IEEE Transactions on, vol. 5, no. 2, pp. 157-166, 1994.
11. S. Hochreiter and J. Schmidhuber, "Long short-term memory, "Neural computation, vol. 9, no. 8, pp. 1735-1780, 1997.
12. A. Graves, N. Jaitly, and A.-R. Mohamed, "Hybrid speech recognitionwith deep bidirectional lstm, " in Automatic Speech Recognitionand Understand ing (ASRU), 2013 IEEE Workshop on. IEEE, 2013, pp. 273-278.
13. H. Sak, A. Senior, and F. Beaufays, "Long short-term memory recurrentneural network architectures for large scale acoustic modeling, "in Fifteenth Annual Conference of the International SpeechCommunication Association (INTERSPEECH). ISCA, 2014.
14. H. Sak, O. Vinyals, G. Heigold, A. Senior, E. McDermott, R. Monga, and M. Mao, "Sequence discriminative distributedtraining of long short-term memory recurrent neural networks, "in Fifteenth Annual Conference of the International Speech CommunicationAssociation (INTERSPEECH). ISCA, 2014.
15. X. Li and X. Wu, "Constructing long short-term memory baseddeep recurrent neural networks for large vocabulary speech recognition, "arXiv preprint arXiv: 1410. 4281, 2014.
16. D. Yu, M. L. Seltzer, J. Li, J.-T. Huang, and F. Seide, "Featurelearning in deep neural networks-studies on speech recognitiontasks, " arXiv preprint arXiv: 1301. 3605, 2013.
17. Y. Miao, H. Zhang, and F. Metze, "Distributed learning of multilingualdnn feature extractors using gpus, " in Fifteenth AnnualConference of the International Speech Communication Association(INTERSPEECH). ISCA, 2014.
18. H. Liao, "Speaker adaptation of context dependent deep neuralnetworks, " in Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on. IEEE, 2013, pp. 7947-7951.
19. D. Yu, K. Yao, H. Su, G. Li, and F. Seide, "Kl-divergence regularizeddeep neural network adaptation for improved large vocabularyspeech recognition, " in Acoustics, Speech and SignalProcessing (ICASSP), 2013 IEEE International Conference on. IEEE, 2013, pp. 7893-7897.
20. B. Li and K. C. Sim, "Comparison of discriminative input and outputtransformations for speaker adaptation in the hybrid nn/hmmsystems, " in Eleventh Annual Conference of the InternationalSpeech Communication Association (INTERSPEECH). ISCA, 2010.
21. K. Yao, D. Yu, F. Seide, H. Su, L. Deng, and Y. Gong, "Adaptationof context-dependent deep neural networks for automaticspeech recognition, " in 2012 IEEE Spoken Language TechnologyWorkshop (SLT). IEEE, 2012.
22. F. Seide, G. Li, X. Chen, and D. Yu, "Feature engineeringin context-dependent deep neural networks for conversationalspeech transcription, " in Automatic Speech Recognition and Understand ing(ASRU), 2011 IEEE Workshop on. IEEE, 2011, pp. 24-29.
23. S. P. Rath, D. Povey, K. Vesely, and J. Cernocky, "Improved featureprocessing for deep neural networks, " in Fourteenth AnnualConference of the International Speech Communication Association(INTERSPEECH). ISCA, 2013, pp. 109-113.
24. H. Zhang, Y. Miao, and F. Metze, "Regularizing dnn acousticmodels with Gaussian stochastic neurons, " in Acoustics, Speechand Signal Processing (ICASSP), 2015 IEEE International Conferenceon. IEEE, 2015, pp. 4964-4968.
25. G. Saon, H. Soltau, D. Nahamoo, and M. Picheny, "Speaker adaptationof neural network acoustic models using i-vectors, " in AutomaticSpeech Recognition and Understand ing (ASRU), 2013IEEE Workshop on. IEEE, 2013, pp. 55-59.
26. A. Senior and I. Lopez-Moreno, "Improving dnn speaker independencewith i-vector inputs, " in Acoustics, Speech and SignalProcessing (ICASSP), 2014 IEEE International Conference on. IEEE, 2014, pp. 225-229.
27. Y. Miao, H. Zhang, and F. Metze, "Towards speaker adaptivetraining of deep neural network acoustic models, " in FifteenthAnnual Conference of the International Speech CommunicationAssociation (INTERSPEECH). ISCA, 2014.
28. Y. Miao, L. Jiang, H. Zhang, and F. Metze, "Improvements tospeaker adaptive training of deep neural networks, " in 2014 IEEESpoken Language Technology Workshop (SLT). IEEE, 2014.
29. F. A. Gers, N. N. Schraudolph, and J. Schmidhuber, "Learningprecise timing with lstm recurrent networks, " The Journal of MachineLearning Research, vol. 3, pp. 115-143, 2003.
30. D. Povey, A. Ghoshal, G. Boulianne, L. Burget, O. Glembek, N. Goel, M. Hannemann, P. Motlcek, Y. Qian, P. Schwarz, J. Silovský, G. Stemmer, and K. Veselý, "The kaldi speech recognitiontoolkit, " in Automatic Speech Recognition and Understand ing(ASRU), 2011 IEEE Workshop on. IEEE, 2011, pp. 1-4.
31. M. J. Gales, "Maximum likelihood linear transformations forhmm-based speech recognition, " Computer speech & language, vol. 12, no. 2, pp. 75-98, 1998.
32. G. Hinton, S. Osindero, and Y.-W. Teh, "A fast learning algorithmfor deep belief nets, " Neural computation, vol. 18, no. 7, pp. 1527-1554, 2006.
33. J. Chiu and A. Rudnicky, "Using conversational word burstsin spoken term detection. " in Fourteenth Annual Conference ofthe International Speech Communication Association (INTERSPEECH). ISCA, 2013.
34. J. Chiu, Y. Wang, J. Trmal, D. Povey, G. Chen, and A. Rudnicky, "Combination of fst and cn search in spoken term detection, " inFifteenth Annual Conference of the International Speech CommunicationAssociation (INTERSPEECH). ISCA, 2014.