A neural network for classification with incomplete data: Application to robust ASR

6th International Conference on Spoken Language Processing, ICSLP 2000

Volumn , Issue , 2000, Pages

  Morris, Andrew C ^a   Josifovski, Ljubomir ^c   Bourlard, Hervé ^a,b   Cooke, Martin ^c   Green, Phil ^c  

^a DALLE MOLLE INSTITUTE FOR ARTIFICIAL INTELLIGENCE IDSIA   (Switzerland)

^b EPFL   (Switzerland)

^c UNIVERSITY OF SHEFFIELD   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

NEURAL NETWORKS; SPEECH RECOGNITION;

CLASS PROBABILITIES; CLASSIFICATION PERFORMANCE; CLOSED-FORM EXPRESSION; DATA CLASSIFICATION; FUNCTION PARAMETERS; MULTI LAYER PERCEPTRON; ROBUST AUTOMATIC SPEECH RECOGNITIONS (ASR); ROBUST RECOGNITION;

CLASSIFICATION (OF INFORMATION);

EID: 9644298432     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (17)

1. Ahmed, S. & Tresp, V. (1993) "Some solutions to the missing feature problem in vision", in Advances in Neural Information Processing Systems 5, Morgan Kauffman, San Mateo, pp. 393-400.
2. Bishop, C. (1995) Neural Networks for Pattern Recognition, Clarendon Press, Oxford.
3. Bourlard, H. & Morgan, N. (1993) Connectionist Speech Recognition, Kluwer Academic Publishers, Boston.
4. Chan, L. W. & Fallside, F. (1987) "An adaptive training algorithm for back-propagation networks", Computer Speech and Language 2, pp. 205-218.
5. Hagen, A. & Morris, A. C. (in press) "Comparison of HMM experts with MLP experts in the full combination multi-band approach to robust ASR", Proc. ICSLP-2000.
6. Hagen, A., Morris, A. C. & Bourlard, H. (1998) "Subband based speech recognition in noisy conditions: The Full-Combination approach", Research Report IDIAP-RR 98-15.
7. Hermansky, H., Ellis, D. & Sharma, S. (2000) "Tandem connectionist feature stream extraction for conventional HMM systems", Proc. ICASSP-2000, pp. 1635-1638..
8. Lippmann, R. P. & Carlson, B. A. (1997) "Using missing feature theory to actively select features for robust speech recognition with interruptions, filtering and noise", Proc. Eurospeech'97, pp. 37-40
9. McDermott, E. & Katagiri, S. (1994) "Prototype-based minimum classification error/generalised probabilistic descent training for various speech units", Computer Speech and Language, No. 8, pp. 351-368.
10. Morris, A. C. (2000) "A neural network for classification with missing data", Research Report IDIAP RR 00-23.
11. Morris, A. C., Cooke, M. & Green, P. (1998) "Some solutions to the missing feature problem in data classification, with application to noise robust ASR", Proc. ICASSP'98, pp. 737-740.
12. Morris, A. C., Hagen, A. & Bourlard, H. (1999) "The full-combination subbands approach to noise robust HMM/ANN based ASR", Proc. Eurospeech'99, pp. 599-602.
13. Morris, A. C., Hagen, A., Glotin, H. & Bourlard, H. (in press) "Multi-stream adaptive evidence combination for noise robust ASR", Speech Communication.
14. Schwenk, H. (1999) "Using boosting to improve a hybrid HMM/neural network speech recogniser", Proc. ICASSP'99. pp. 1009-1012.
15. Vizinho, A., Green, P., Cooke, M. & Josifovski, L. (1999) "Missing data theory, spectral subtraction and signal-to-noise estimation for robust ASR: An integrated study", Proc. Eurospeech'99, pp. 2407-2410.
16. White, H. (1989) "Learning in artificial neural networks: A statistical perspective", Neural Computing, 1, pp. 425-464.
17. Young, S. J. & Woodland, P. C. (1993) HTK Version 1.5: User, Reference and Programmer Manual, Cambridge University Engineering Dept., Speech Group.