Discriminative language modeling using simulated ASR errors

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

Volumn , Issue , 2010, Pages 1049-1052

  Jyothi, Preethi ^a   Fosler Lussier, Eric ^a  

^a The Ohio State University   (United States)

Author keywords

Confusion matrix; Language modeling; Perceptron algorithm; Weighted finite state transducers

Indexed keywords

COMPUTATIONAL LINGUISTICS; GRAPH ALGORITHMS; IMAGE RESOLUTION; MAXIMUM LIKELIHOOD; SPEECH COMMUNICATION; SPEECH RECOGNITION; TRANSDUCERS;

CONFUSION MATRICES; DISCRIMINATIVE LANGUAGE MODELING; LANGUAGE MODEL; LARGE VOCABULARY SPEECH RECOGNITION; MAXIMUM LIKELIHOOD CRITERIA; PERCEPTRON ALGORITHMS; WEIGHTED FINITE-STATE TRANSDUCERS; WORD ERROR RATE REDUCTIONS; ACOUSTICS MODEL; CONFUSION MATRIX; DISCRIMINATIVE LANGUAGE MODELS; LOG LIKELIHOOD; PHONETIC CONFUSIONS; PRONUNCIATION MODELLING; TRAINING DATA;

MODELING LANGUAGES;

EID: 79959849984     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (10)

1. Chen, Z., Lee, K-F. and Li, M. J., "Discriminative training on language model", Proceedings of the Sixth International Conference on Spoken Language Processing, Beijing, 2000.
2. Kuo, H-K. J., Fosler-Lussier, E., Jiang, H. and Lee, C-H., "Discriminative training of language models for speech recognition", Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Florida, 2002.
3. Roark, B., Saraclar, M., Collins, M. and Johnson, M., "Discriminative language modeling with conditional random fields and the perceptron algorithm", Proceedings of the 43rd Meeting of the Association for Compuational Linguistics, 507-514, 2005.
4. Lehr, M., and Shafran, I., "Discriminatively estimated joint acoustic, duration and language model for speech recognition", Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Dallas, 2010.
5. Jyothi, P. and Fosler-Lussier, E., "A comparison of audio-free speech recognition error prediction methods", Proceedings of Interspeech, Brighton, 2009.
6. Huang, J-T., Li, X. and Acero, A., "Discriminative training methods for language models using conditional entropy criteria", Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Dallas, 2010.
7. Fosler-Lussier, E., Amdal, I. and Kuo, H-K. J., "A framework for predicting speech recognition errors", Speech Communication, 46:153-170, 2005. (Pubitemid 40753200)
8. Collins, M., "Discriminative training methods for hidden markov models: Theory and experiments with perceptron algorithms", Proceedings of Empirical Methods in Natural Language Processing, 1-8, 2002.
9. Allauzen, C., Mohri, M. and Roark, B., "Generalized algorithms for constructing language models", Proceedings of the 41st Meeting of the Association for Computational Linguistics, 40-47, 2003.
10. Young, S., "The HTK Hidden Markov Model Toolkit: Design and Philosophy", Online: http://htk.eng.cam.ac.uk, 1993.