I-vector estimation using informative priors for adaptation of deep neural networks

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

Volumn 2015-January, Issue , 2015, Pages 2872-2876

  Karanasou, Penny ^a   Gales, Mark ^a   Woodland, Philip ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

Deep neural networks; I vectors; Prior information; Speaker adaptation

Indexed keywords

SPEECH COMMUNICATION; SPEECH RECOGNITION; VECTORS;

DEEP NEURAL NETWORKS; I VECTORS; INFORMATIVE PRIORS; LOW-DIMENSIONAL REPRESENTATION; PRIOR INFORMATION; RELATIVE REDUCTION; SPEAKER ADAPTATION; STATE OF THE ART;

VECTOR SPACES;

EID: 84959162419     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (22)

1. G. Saon, H. Soltau, D. Nahamoo, and M. Picheny, "Speaker adaptation of neural network acoustic models using i-vectors, " in Proc. ASRU, 2013, pp. 55-59.
2. A. Senior and I. Lopez-Moreno, "Improving DNN speaker independence with i-vector inputs, " in Proc. ICASSP, 2014, pp. 225-229.
3. P. Karanasou, Y. Wang, M. J. F. Gales, and P. C. Woodland, "Adaptation of deep neural network acoustic models using factorised i-vectors, " in Proc. Interspeech, 2014, pp. 2180-2184.
4. O. Siohan and M. Bacchiani, "iVector-based acoustic data selection, " in Proc. Interspeech, 2013, pp. 657-661.
5. A. Kanagasundaram, R. Vogt, D. Dean, S. Sridharan, and M. Mason, "i-Vector based speaker recognition on short utterances, " in Proc. Interspeech, 2011, pp. 2341-2344.
6. P. Kenny, "Joint factor analysis of speaker and session variability: Theory and algorithms, " in Technical Report CRIM-06/08-14, 2006.
7. -, "Bayesian speaker verification with heavy-tailed priors, " in Proc. Odyssey-10, 2010.
8. D. Garcia-Romero and C. Y. Espy-Wilson, "Analysis of i-vector length normalization in speaker recognition systems, " in Proc. Interspeech, 2011, pp. 249-252.
9. R. Travadi, M. V. Segbroeck, and S. Narayanan, "Modified-prior i-vector estimation for language identification of short duration utterances, " in Proc. Interspeech, 2014, pp. 3037-3041.
10. M. J. F. Gales, "Transformation smoothing for speaker and environmental adaptation, " in Proc. Eurospeech, 1997.
11. C. Breslin, K. Chin, M. Gales, K. Knill, and H. Xu, "Prior information for rapid speaker adaptation, " in Proc. Interspeech, 2010, pp. 1644-1647.
12. L. Chen, M. J. F. Gales, V. Wan, J. Latorre, and M. Akamine, "Exploring rich expressive information from audiobook data using cluster adaptive training, " in Proc. Interspeech, 2012, pp. 959-962.
13. M. J. F. Gales, "Cluster adaptive training of hidden Markov models, " IEEE Transactions on Speech and Audio Processing, vol. 8, pp. 417-428, 1999.
14. D. A. Reynolds, T. F. Quatieri, and R. B. Dunn, "Speaker verification using adapted Gaussian mixture models, " Digital Signal Processing, vol. 10, no. 1-3, pp. 19-41, 2000.
15. D. Graff, "The 1996 broadcast news speech and language-model corpus, " in Proc. 1997 DARPA Speech Recognition Workshop, 1997, pp. 11-14.
16. D. S. Pallett, J. G. Fiscus, A. Martin, and M. A. Przybocki, "1997 broadcast news benchmark test results: English and non-english, " in Proc. 1998 DARPA Broadcast News Transcription and Understanding Workshop, 1998, pp. 5-11.
17. S. E. Tranter, M. J. F. Gales, R. Sinha, S. Umesh, and P. C. Woodland, "The development of the Cambridge University RT-04 diarisation system, " in Proc. Fall 2004 Rich Transcription Workshop (RT-04), 2004.
18. G. Hinton, L. Deng, D. Yu, G. Dahl, A. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T. Sainath, and B. Kingsbury, "Deep neural networks for acoustic modeling in speech recognition, " IEEE Signal Processing Magazine, vol. 29, no. 6, pp. 82-97, 2012.
19. M. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition, " Computer Speech and Language, vol. 12, no. 75-98, 1998.
20. G. Dahl, D. Yu, L. Deng, and A. Acero, "Context-dependent pretrained deep neural networks for large-vocabulary speech recognition, " IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 1, pp. 30-42, 2012.
21. D. Johnson, "Quicknet, " www1. icsi. berkeley. edu/Speech/qn. html.
22. F. Seide, G. Li, X. Chen, and D. Yu, "Feature engineering in context-dependent deep neural networks for conversational speech transcription, " in Proc. ASRU, 2011, pp. 24-29.