THE FULL COMBINATION SUB-BANDS APPROACH TO NOISE ROBUST HMM/ANN BASED ASR

6th European Conference on Speech Communication and Technology, EUROSPEECH 1999

Volumn , Issue , 1999, Pages 599-602

  Morris, Andrew ^a   Hagen, Astrid ^a   Bourlard, Hervé ^a,b  

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

^b EPFL   (Switzerland)

Author keywords

HMM ANN hybrid; missing feature theory; multiband ASR; noise robust ASR

Indexed keywords

SPEECH RECOGNITION;

CLEAN SPEECH; DATA MISMATCH; HMM/ANN HYBRID; MISSING FEATURE THEORIES; MULTI BAND; MULTIBAND ASR; NOISE ROBUST; NOISE ROBUST ASR; PERFORMANCE; SUBBANDS;

SPEECH COMMUNICATION;

EID: 85135272651     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (16)

1. Allen, J. B. (1994) “How do humans process and recognise speech?”, IEEE Trans. on Speech and Signal Processing, Vol.2, No.4, pp.567-576.
2. Berthommier, F. & Glotin, H. (1999) “SNR-feature mapping for robust multistream speech recognition”, Proc. ICPhS'99, (in press).
3. Bourlard, H., Dupont, S. & Ris, C. (1996) “Multistream speech recognition”, Research Report IDIAP-RR-96-07.
4. Bourlard, H. & Morgan, N. (1997) “Hybrid HMM/ANN Systems for Speech Recognition: Overview and New Research Directions”, Proc. “International School on Neural Nets: Adaptive Processing of Temporal Information”
5. Cole, R.A., Noel, T., Lander, L. & Durham, T. (1995) “New telephone speech corpora at CSLU”, Proc. European Conf. on Sp. Comm. and Tech., 1, pp. 821-824.
6. Fletcher, H. (1922) “The nature of speech and its interpretation”, J. Franklin Inst., 193(6), pp.729-747.
7. Hagen, A., Morris, A.C. & Bourlard, H. (1998) “Sub-band based speech recognition in noisy conditions: The Full-Combination approach”, Research Report IDIAP-RR 98-15.
8. Hagen, A., Morris, A.C. & Bourlard, H. (1999) “Different weighting schemes in the full combination sub-bands approach for noise robust ASR”, Proc. Workshop on Robust Methods for Speech Recognition in Adverse Conditions.
9. Hermansky, H. (1990) “Perceptual linear predictive (PLP) analysis of speech”, J. Acoust. Soc. Am., 87(4), pp.1738-1752.
10. Hermansky, H. & Morgan, N. (1994) “RASTA processing of speech”, IEEE Trans. on Speech and Audio Processing, 2(4), pp.578-589.
11. Hermansky, H., Tibrewela, S. & Pavel, M. (1996) “Towards ASR on partially corrupted speech”, Proc ICSLP'96, pp. 462-465.
12. 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
13. Morgan, N., Bourlard, H. & Hermansky, H. (1998) “Automatic speech recognition: an auditory perspective”, Research Report IDIAP-RR 98-17.
14. 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.
15. Varga, A., Steeneken, H.J.M., Tomlinson, M. & Jones, D. (1992) “The Noisex-92 study on the effect of additive noise on automatic speech recognition”, Tech. Rep. DRA Speech Research Unit.
16. de Veth, J., de Wet, F., Cranen, B. & Boves, L. (1999) “Missing feature theory in ASR: make sure you missing the right type of features”, Proc. Workshop on Robust Methods for Speech Recognition in Adverse Conditions.