An investigation of augmenting speaker representations to improve speaker normalisation for DNN-based speech recognition

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

Volumn 2015-August, Issue , 2015, Pages 4610-4613

  Huang, Hengguan ^a   Sim, Khe Chai ^a  

^a NATIONAL UNIVERSITY OF SINGAPORE   (Singapore)

Author keywords

augmented speaker representation; deep neural network; speaker normalisation; speech recognition

Indexed keywords

AUDIO SIGNAL PROCESSING; DEEP NEURAL NETWORKS; LOUDSPEAKERS; SPEECH; SPEECH COMMUNICATION; VECTOR SPACES;

AUGMENTED SPEAKER REPRESENTATION; AUTOMATIC SPEECH RECOGNITION; BOTTLENECK FEATURES; FINE GRAINS; PERFORMANCE GAIN; POSTERIOR PROBABILITY; SPEAKER INDEPENDENTS; SPEAKER NORMALISATION;

SPEECH RECOGNITION;

EID: 84946035423     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2015.7178844     Document Type: Conference Paper

References (12)

1. G. Hinton, L. Deng, D. Yu, G. Dahl, A. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T. N. Sainath, and B. Kingsbury, Deep neural networks for acoustic modeling in speech recognition, IEEE Signal Processing Magazine, vol. 29, pp. 82-97, 2012
2. G. Saon, H. Soltau, D. Nahamoo, and M. Picheny, Speaker adaptation of neural network acoustic models using i-vectors, in ASRU, 2013
3. Y. Miao, H. Zhang, and F. Metze, Towards speaker adaptive training of deep neural network acoustic models, in Proc. Interspeech, 2014
4. P. Kenny, G. Boulianne, P. Ouellet, and P. Dumouchel, Speaker and session variability in GMM-based speaker verification, IEEE Transactions on Audio, Speech &Language Processing, vol. 15, no. 4, pp. 14481460, 2007
5. C. J. 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, 1995
6. M.J.F. Gales, Maximum likelihood linear transformations for hmm-based speech recognition, Computer Speech &Language, vol. 12, 1998
7. Frank Seide, Gang Li, Xie Chen, and Dong Yu, Feature engineering in context-dependent deep neural networks for conversational speech transcription, in ASRU, 2011, pp. 24-29
8. Shaofei Xue, O. Abdel-Hamid, Hui Jiang, Lirong Dai, and Qingfeng Liu, Speaker and session variability in GMMbased speaker verification, IEEE/ACM Transactions on Audio, Speech &Language Processing, vol. 22, no. 12, pp. 1713-1725, 2014
9. M. Ferras and H. Bourlard, MLP-based factor analysis for tandem speech recognition, in IEEE International Conference on Acoustics, Speech and Signal Processing. 2013, IEEE
10. Hagai Aronowitz, Dror Irony, and David Burstein, Modeling intra-speaker variability for speaker recognition, in Proc. Interspeech, 2005
11. Sibel Yaman, Jason Pelecanos, and Ruhi Sarikaya, Bottleneck features for speaker recognition, in Proc. Odyssey, 2012, vol. 12
12. D. B. Paul and J. M. Baker, The design for the Wall Street Journal-based CSR corpus, in Proc. ICSLP, 1992