Multi-style MLP features for BN transcription

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

Volumn , Issue , 2010, Pages 4866-4869

  Le, Viet Bac ^a   Lamel, Lori ^a   Gauvain, Jean Luc ^a  

^a CNRS   (France)

Author keywords

BN transcription; Condition specific adaptation; MLP features

Indexed keywords

ACOUSTICS MODEL; BN TRANSCRIPTION; CONDITION; CONDITION-SPECIFIC ADAPTATION; DISCRIMINATIVE FEATURES; MULTI LAYER PERCEPTRON FEATURE; MULTILAYERS PERCEPTRONS; PARTICULAR CONDITION; PERFORMANCE; SPECIFIC ADAPTATIONS;

TRANSCRIPTION;

EID: 78049384951     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2010.5495116     Document Type: Conference Paper

References (18)

1. H. Hermansky, "Perceptual linear prediction (PLP) analysis for speech," Journal of the Acoustical Society of America, vol. 87, pp. 1738-1752, April 1990.
2. P. Fousek, L. Lamel, and J-.L. Gauvain, "Transcribing broadcast data using MLP features," in Interspeech 2008, Brisbane, Australia, September 2008, pp. 1433-1436.
3. P. Schwarz, P. Matějka, and J. Černocky, "Towards lower error rates in phoneme recognition," in TSD'04, Brno, Czech Republic, September 2004, pp. 465-472.
4. Q. Zhu, A. Stolcke, B. Y. Chen, and N. Morgan, "Using MLP features in SRI's conversational speech recognition system," in Interspeech'05, Lisbon, 2005, pp. 2141-2144.
5. J. Park et al., "Efficient generation and use of MLP features for Arabic speech recognition," in Interspeech'09, Brighton, UK, September 2009, pp. 236-239.
6. J-.L. Gauvain, L. Lamel, and G. Adda, "The LIMSI Broadcast News Transcription System," Speech Communication, vol. 37, no. 1-2, pp. 89-108, May 2002.
7. J. Despres et al., "Modeling northern and southern varieties of Dutch for STT," in Interspeech'09, Brighton, UK, September 2009, pp. 96-99.
8. R. Schwartz et al., "Modeling those F-conditions - or not," in Proc. DARPA Speech Recognition Workshop, Chantilly, VA, February 1997, pp. 115-118.
9. S. Galliano et al., "The ESTER 2 evaluation campaign for the rich transcription of French radio broadcasts," in Interspeech'09, Brighton, U.K., September 2009.
10. J.-L. Gauvain and C.H. Lee, "Maximum a posteriori estimation for multivariate gaussian mixture observations of markov chains," IEEE Trans. on Speech and Audio Processing, vol. 2, no. 2, pp. 291-298, April 1994.
11. A. Stolcke et al., "Cross-domain and cross-language portability of acoustic features estimated by multilayer perceptrons," in ICASSP'06, Toulouse, France, May 2006, vol. 1, pp. 321-324.
12. J. Neto et al., "Speaker adaptation for hybrid HMM-ANN continuous speech recognition system," in Eurospeech' 95, Madrid, Spain, 1995, pp. 2171-2174.
13. X. Li and J. Bilmes, "Regularized adaptation of discriminative classifiers," in ICASSP'06, Toulouse, France, September 2006, vol. 1, pp. 237-240.
14. J-.L. Gauvain et al., "Where are we in transcribing French broadcast news?," in Interspeech'05, Lisbon, Portugal, September 2005, pp. 1665-1668.
15. P. Fousek, Extraction of Features for Automatic Recognition of Speech Based on Spectral Dynamics, Ph.D. thesis, Czech Technical University, March 2007.
16. F. Grézl and P. Fousek, "Optimizing bottle-neck features for LVCSR," in ICASSP'08, Las Vegas, 2008, pp. 4729-4732.
17. G. Adda et al., "Le système TRS du LIMSI," in ESTER Workshop, Paris, France, April 2009.
18. C.J. Leggetter and P.C. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden markov models," Computer Speech and Language, vol. 9, no. 2, pp. 171-185, April 1995.