MLP based hierarchical system for task adaptation in ASR

Proceedings of the 2009 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2009

Volumn , Issue , 2009, Pages 365-370

  Pinto, Joel ^a,b   Magimai Doss, Mathew ^a   Bourlard, Hervé ^a,b  

^a IDIAP RESEARCH INSTITUTE   (Switzerland)

^b EPFL   (Switzerland)

Author keywords

[No Author keywords available]

Indexed keywords

ADAPTATION SCHEME; AUTOMATIC SPEECH RECOGNITION; CONVERSATIONAL TELEPHONE SPEECH; ERROR RATE; HIERARCHICAL APPROACH; ISOLATED WORD RECOGNITION; MLP CLASSIFIERS; MULTI LAYER PERCEPTRON; PHONEBOOK; TASK ADAPTATION; TEMPORAL INFORMATION; WORD ERROR RATE;

HIERARCHICAL SYSTEMS;

SPEECH RECOGNITION;

EID: 77949374930     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ASRU.2009.5373383     Document Type: Conference Paper

References (19)

1. N. Morgan et al., "Pushing the Envelope - Aside," IEEE Signal Process. Magazine, vol. 22, no. 5, pp. 81-88, 2005.
2. A. Stolcke et al., "Recent Innovations in Speech-to-Text Transcription at SRI-ICSI-UW," IEEE Trans. Audio. Speech. Language. Process., vol. 14, no. 5, pp. 1729-1744, 2006.
3. Q. Zhu, B. Chen, N. Morgan, and A. Stolcke, "On Using MLP Features in LVCSR," Proc. of Interspeech, pp. 921-924, 2004.
4. P. Fousek, L. Lamel, and J.-L. Gauvain, "Transcribing Broadcast Data using MLP Features," Proceedings of Interspeech, 2008.
5. J. Park, F. Diehl, M. Gales, M. Tomalin, and P. Woodland, "Training and Adapting MLP Features for Arabic Speech Recognition," Proc. of IEEE Conf. Acoust. Speech Signal Process. (ICASSP), 2009.
6. M. Richard and R. Lippmann, "Neural Network Classifiers Estimate Bayesian a posteriori Probabilities," Neural Computation, vol. 3, pp. 461-483, 1991.
7. H. Bourlard and N. Morgan, Connectionist Speech Recognition - A Hybrid Approach. Kluwer Academic Publishers, 1994.
8. H. Hermansky, D. Ellis, and S. Sharma, "Tandem Connectionist Feature Extraction for Conventional HMM Systems," Proc. of IEEE Conf. Acoust. Speech Signal Process. (ICASSP), pp. 1635-1638, 2000.
9. J. Pinto, G. Sivaram, M. Magimai.-Doss, H. Hermansky, and H. Bourlard, "Analysis of MLP based Hierarchical Phoneme Posterior Probability Estimator," Idiap Research Institute, Tech. Rep., 2009.
10. J. Pinto, B. Yegnanarayana, H. Hermansky, and M. Magimai.-Doss, "Exploiting Contextual Information for Improved Phoneme Recognition," Proc. of IEEE Conf. Acoust. Speech Signal Process. (ICASSP), pp. 4449-4452, 2008.
11. H. Ketabdar and H. Bourlard, "Hierarchical Integration of Phonetic and Lexical Knowledge in Phone Posterior Estimation," Proc. of IEEE Conf. Acoust. Speech Signal Process. (ICASSP), pp. 4065-4068, 2008.
12. A. Stolcke et al., "Further Progress in Meeting Recognition: The ICSI-SRI Spring 2005 Speech-to-text Evaluation System," Second Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms, pp. 463-475, 2005.
13. X. Li and J. Bilmes, "Regularized Adaptation of Discriminative Classifiers," Proc. of IEEE Conf. Acoust. Speech Signal Process. (ICASSP), 2006.
14. S. Ikbal, "Nonlinear Feature Transformations for Noise Robust Speech Recognition," Ph.D. dissertation, École Polytechnique Fédérale de Lausanne (EPFL), Switzerland, 2004.
15. J. Pitrelli et al., "PhoneBook: A Phonetically-rich Isolated-word Telephone Speech Database," Proc. of IEEE Conf. Acoust. Speech Signal Process. (ICASSP), pp. 101-104, 1995.
16. T. Hain et al., "The Development of AMI System for Transcription of Speech in Meetings," in Machine learning for Multimodal Interaction: 2nd International Workshop, Revised Selected Papers, S. Renals and S. Bengio, Eds. Springer-Verlag, 2005, no. 3869, pp. 344-356.
17. S. Dupont, H. Bourlard, O. Deroo, V. Fontaine, and J.-M. Boite, "Hybrid HMM/ANN Systems for Training Independent Tasks: Experiments on 'PhoneBook' and Related Improvements," Proc. of IEEE Conf. Acoust. Speech Signal Process. (ICASSP), pp. 1767-1770, 1997.
18. S. Fitt, "Documentation and User Guide to UNISYN Lexicon and Post-lexical Rules," Center for Speech Technology Research, University of Edinburgh, Tech. Rep., 2000.
19. L. Gillick and S. Cox, "Some Statistical Issues in the Comparison of Speech Recognition Algorithms," Proc. of IEEE Conf. Acoust. Speech Signal Process. (ICASSP), pp. 532-535, 1989.