On the estimation and the use of confusion-matrices for improving ASR accuracy

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

Volumn , Issue , 2009, Pages 1599-1602

  Morales, Omar Caballero ^a   Cox, Stephen ^a  

^a UNIVERSITY OF EAST ANGLIA   (United Kingdom)

Author keywords

Confusion matrix modelling; Metamodels; Non negative matrix factorization

Indexed keywords

ALTERNATIVE METHODS; DATA SPARSITY; MATRIX; MATRIX ESTIMATION; META MODEL; NONNEGATIVE MATRIX FACTORIZATION; RECOGNITION ACCURACY; RECOGNITION ERROR; TRAINING DATA; WORD RECOGNITION;

BLIND SOURCE SEPARATION; ERROR DETECTION; ESTIMATION; FACE RECOGNITION; FACTORIZATION; LIGHT MEASUREMENT; PATTERN RECOGNITION SYSTEMS; REMELTING; SPEECH COMMUNICATION; SPEECH INTELLIGIBILITY; SPEECH RECOGNITION;

MATRIX ALGEBRA;

EID: 70450182941     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (8)

1. Caballero, Omar and Cox, Stephen, "Modelling confusion matrices to improve speech recognition accuracy, with an application to dysarthric speech," Interspeech 2007, 2007.
2. -, "Application of weighted finite-state transducers to improve recognition accuracy for dysarthric speech," Interspeech 2008, 2008.
3. Cox, Stephen, "On estimation of a speakers confusion matrix from sparse data," Interspeech 2008, 2008.
4. Bunnel, H.T. and Polikoff, J.B., "The nemours database of dysarthric speech," Proceedings of ICSLP, 1996.
5. Lee, D.D. and Seung, H.S., "Learning the parts of objects by nonnegative matrix factorization," Nature, 1999.
6. -, "Algorithms for non-negative matrix factorization, " Advances in Neural Information Processing Systems, vol. 13, pp. 556-562, 2001.
7. Matsumasa, Hironori, Takiguchi, Tetsuya, Ariki, Yasuo, LI, Ichao, and Nakabayashi, Toshitaka, "Integration of meta-model and acoustic model for speech recognition," Interspeech 2008, 2008.
8. Leggetter, C.J. and Woodland, P.C., "Maximum likelihood linear regression for speaker adaptation of continuous density hidden markov models," Computer Speech and Language, vol. 9, no. 2, pp. 171-85, 1995.