Deep neural network trained with speaker representation for speaker normalization

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

Volumn , Issue , 2014, Pages 6329-6333

  Tang, Yun ^a   Mohan, Aanchan ^b   Rose, Richard C ^b   Ma, Chengyuan ^a  

^a NUANCE COMMUNICATIONS   (United States)

^b MCGILL UNIVERSITY   (Canada)

Author keywords

Neural networks; speaker adaptation; speaker normalization

Indexed keywords

FEATURE EXTRACTION; HIDDEN MARKOV MODELS; NEURAL NETWORKS; SPEECH RECOGNITION;

AUTOMATIC SPEECH RECOGNITION; DEEP NEURAL NETWORKS; DISCRIMINATIVE FEATURES; INCORPORATING PRIOR KNOWLEDGE; SPEAKER ADAPTATION; SPEAKER NORMALIZATION; SPEAKER VARIABILITY; SPECTRAL MAGNITUDES;

SIGNAL PROCESSING;

EID: 84905265988     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2014.6854822     Document Type: Conference Paper

References (18)

1. G. Hinton, L. Deng, D. Yu, et al., "Deep neural networks for acoustic modeling in speech recognition," IEEE Signal Processing Magazine, vol. 29, pp. 82-97, November 2012.
2. Daniel P. W. Ellis Hynek Hermansky and Sangita Sharma, "Tandem connectionist feature extraction for conventional HMM systems," in ICASSP, 2000, pp. 1635-1638.
3. T. Sainath, B. Kingsbury, and B. Ramabhadran, "Auto-encoder bottleneck features using deep belief networks," in ICASSP, 2012, pp. 4153-4156.
4. C. Leggetter and P. Woodland, "Flexible speaker adaptation using maximum likelihood linear regression," in the ARPA Spoken Language Technology Workshop, 1995, pp. 104-109.
5. M. J. F. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition," Computer Speech and Language, vol. 12, pp. 75-98, 1998.
6. M. Ferras and H. Bourlard, "MLP-based factor analysis for tandem speech recognition," in ICASSP, 2013.
7. O. Abdel-Hamid and H. Jiang, "Fast speaker adaptation of hybrid NN/HMM model for speech recognition based on discriminative learning of speaker code," in ICASSP, 2013.
8. O. Abdel-Hamid and H. Jiang, "Rapid and effective speaker adaptation of convolutional neural network based models for speech recognition," in INTERSPEECH, 2013.
9. A. Krizhevsky, I. Sutskever, and G. Hinton, "Imagenet classification with deep convolutional neural networks," in NIPS, 2012.
10. G. Dahl, T. Sainath, and G. Hinton, "Improving deep neural network for LVCSR using recified linear units and dropout," in ICASSP, 2013.
11. M. Zeiler, M. Ranzato, R. Monga, M. Mao, K. Yang, Q. Le, P. Nguyen, A. Senior, V. Vanhoucke, J. Dean, and G. Hinton, "On rectified linear units for speech processing," in ICASSP, 2013.
12. J. Neto, L. Almeida, M. Hochberg, C. Martins, L. Nunes, S. Renals, and T. Robinson, "Speaker adaptation for hybrid HMM-ANN continuous speech recognition system," in Eurospeech, 1995, pp. 2171-2174.
13. R. Gemello, F. Mana, S. Scanzio, P. Laface, and R. de Mori, "Linear hidden transformations for adaptation of hybrid ANN/HMM models," Speech Communication, vol. 49, no. 10-11, pp. 827-835, 2007.
14. T. Anastasakos, J. McDonough, R. Schwartz, and J. Makhoul, "A compact model for speaker-adaptive training," in ICSLP, 1996, vol. 2, pp. 1137-1140 vol. 2.
15. Tijmen Tieleman, "Gnumpy: an easy way to use GPU boards in python," Tech. Rep., University of Toronto, Department of Computer Science, 2010.
16. Volodymyr Mnih, "Cudamat: a CUDA-based matrix class for python," Tech. Rep., University of Toronto, Department of Computer Science, 2009.
17. Z. Tuske, C. Plahl, and R. Schluter, "A study on speaker normalized MLP features in LVCSR," in Interspeech, Auguest 2011, pp. 1089-1092.
18. Y. Wang and M. J. F. Gales, "Tandem system adaptation using multiple linear feature transforms," in ICASSP, 2013.