Transcribing broadcast data using MLP features

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

Volumn , Issue , 2008, Pages 1433-1436

  Fousek, Petr ^a   Lamel, Lori ^a   Gauvain, Jean Luc ^a  

^a CNRS   (France)

Author keywords

Bottle neck; Broadcast transcription; Discriminative training; LP TRAP; MLP

Indexed keywords

ADAPTATION TECHNIQUES; BROADCAST DATA; BROADCAST TRANSCRIPTION; CEPSTRAL FEATURES; COMBINED FEATURES; DISCRIMINATIVE FEATURES; DISCRIMINATIVE TRAINING; FEATURE SETS; LP-TRAP; MLP; MODEL TRAINING; MULTI LAYER PERCEPTRON; SYSTEM-BASED; TEST CONDITION;

BOTTLES; SPEECH COMMUNICATION; SPEECH RECOGNITION;

TRANSCRIPTION;

EID: 84867209138     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (13)

1. J. Zheng and al., "Combining dicsriminative feature, transform, and model training for large vocabulary speech recognition," in ICASSP 2007. Hononulu: IEEE, April 2007.
2. Q. Zhu, A. Stolcke, B. Y. Chen, and N. Morgan, "Using MLP features in SRI's conversational speech recognition system," in INTERSPEECH 2005, 2005, pp. 2141-2144.
3. A. Stolcke and al., "Recent innovations in speech-to-text transcription at sri-icsi-uw," IEEE Trans. on Audio, Speech and Language Processing, vol. 14, September 2006.
4. P. Fousek, Extraction of Features for Automatic Recognition of Speech Based on Spectral Dynamics. Prague: PhD thesis, Czech Technical Univ., Faculty Electrical Engineering, March 2007.
5. F. Grézl and P. Fousek, "Optimizing bottle-neck features for LVCSR," in ICASSP'08, Las Vegas, 2008.
6. P. Fousek, L. Lamel, and J. Gauvain, "On the Use of MLP Features for Broadcast News Transcription," in TSD 2008, September 2008.
7. J. Gauvain, L. Lamel, and G. Adda, "The LIMSI Broadcast News Transcription System," Speech Communication, vol. 37, no. 1-2, pp. 89-108, 2002.
8. L. Lamel, A. Messaoudi, and L. G. J, "Improved Acoustic Modeling for Transcribing Arabic Broadcast Data," in InterSpeech'07, Antwerp, August 2007.
9. C. Leggetter and P. 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, 1995.
10. L. Lamel, A. Messaoudi, and J. Gauvain, " Investigating Morphological Decomposition for Transcription of Arabic Broadcast News and Broadcast Conversation Data," in Interspeech 2008, September 2008.
11. H. Schwenk, "Continuous space language models," Computer Speech and Language, vol. 21, pp. 492-518, 2007.
12. M. Athineos, H. Hermansky, and D. P. Ellis, "LP-TRAP: Linear predictive temporal patterns," in International Conference on Spoken Language Processing (ICSLP), 2004.
13. J. Fiscus, "A Post-Processing System to Yield Reduced Word Error Rates: Recogniser Output Voting Error Reduction (ROVER)," Santa Barbara, pp. 347-352, 1997.