Context dependent modelling approaches for hybrid speech recognizers

Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

Volumn , Issue , 2010, Pages 2950-2953

  Abad, Alberto ^a   Pellegrini, Thomas ^a   Trancoso, Isabel ^a,b   Neto, João ^a,b  

^a INESC ID   (Portugal)

^b INSTITUTO SUPERIOR TÉCNICO   (Portugal)

Author keywords

Connectionist system; Context modeling; Speech recognition

Indexed keywords

HYBRID SYSTEMS; SPEECH; SPEECH COMMUNICATION; SPEECH PROCESSING;

BROADCAST NEWS TRANSCRIPTIONS; CONNECTIONIST APPROACH; CONNECTIONIST SYSTEMS; CONTEXT DEPENDENT; CONTEXT MODELING; CONTEXT MODELLING; SPEECH RECOGNIZER; WORD ERROR RATE REDUCTIONS; CONTEXT DEPENDENT MODELING; CONTEXT MODELS; GAUSSIAN SYSTEMS; MAIN CLAIMS; MODELING APPROACH; TRIPHONES;

SPEECH RECOGNITION;

EID: 79959815770     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (12)

1. Lippmann, R. P., "Review of neural networks for speech recognition", Neural Computation, 1(1):1-38, 1990.
2. Morgan, N. and Bourlad, H., "An introduction to hybrid HMM/connectionist continuous speech recognition", IEEE Signal Processing Magazine, 12(3):25-42, 1995.
3. Bourlard, H., Morgan, N., Wooters, C. and Renals, S., "CDNN: A Context Dependent Neural Network For Continuous Speech Recognition", In Proc. ICASSP'92, II:349-352, 1992.
4. Franco, H., Cohen, M., Morgan, N., Rumelhart, D. and Abrash, V., "Context-dependent Connectionist Probability Estimation in a Hybrid Hidden Markov Model-Neural Net Speech Recognition System", Computer Speech and Language, 8(3):211-222, 1994.
5. Rottland, J. and Rigoll, G., "Tied posteriors: an approach for effective introduction of context dependency in hybrid NN/HMM LVCSR", In Proc. ICASSP'00, III:1241-1244, 2000.
6. Meinedo, H., Caseiro, D., Neto, J. and Trancoso, I., "AUDIMUS. media: A Broadcast News speech recognition system for the European Portuguese language", In Proc. of Int. Conf. of Computational Processing of Portuguese Language (PROPOR), 2003.
7. Abad, A. and Neto, J., "Incorporating acoustical modeling of phone transitions in an hybrid ANN/HMM speech recognizer", In Proc. Interspeech'08, 2394-2397, 2008.
8. Pavelka, T. and Kral, P., "Neural network acoustic model with decision tree clustered triphones", In Proc. of IEEE Workshop on Machine Learning for Signal Processing (MLSP'08), 216-220, 2008.
9. Paul, D. and Baker, J. M., "The Design for the Wall Street Journal-based CSR Corpus", in DARPA Speech and Natural Language Workshop, 1992.
10. Woodland, P.C., Odell, J.J., Valtchev, V. and Young, S.J., "Large Vocabulary Continuous Speech Recognition Using HTK", In Proc. ICASSP'94, II:125-128, 1994.
11. Young, S. et al. "HTK - Hidden Markov Model Toolkit", Manual, 2006. Online: http://htk.eng.cam.ac.uk/
12. Theodoris, S. and Koutroumbas, K., "Pattern recognition", Academic Press, 1998.