Feature vector selection to improve ASR robustness in noisy conditions

EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology

Volumn , Issue , 2001, Pages 201-204

  De Veth, Johan ^a   Mauuary, Laurent ^b   Noe, Bernhard ^c   De Wet, Febe ^a   Sienel, Juergen ^c   Boves, Louis ^a   Jouvet, Denis ^b  

^a RADBOUD UNIVERSITY NIJMEGEN   (Netherlands)

^b ORANGE LABS   (France)

^c NOKIA RESEARCH CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

FACE RECOGNITION; FEATURE EXTRACTION; SPEECH COMMUNICATION;

ACOUSTIC VECTORS; FEATURE VECTOR SELECTION; NOISY CONDITIONS; NON SPEECH; RECOGNITION ACCURACY; RECOGNITION TIME; VARIABLE FRAME RATE; VOICE ACTIVITY DETECTION;

SPEECH RECOGNITION;

EID: 84938647987     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (9)

1. De Veth, J., Cranen, B., and Boves, L., "Acoustic features and distance measure to reduce vulnerability of ASR performance due to the presence of a communication channel and/or background noise", in: Robustness in language and speech technology, J.-C. Junqua and G. van Noord (Eds), Kluwer, 9 -45, 2001.
2. McAuley, R.J. and Malpass, M.L., "Speech enhancement using a soft-decision noise suppression filter", IEEE Trans. Acoustics, Speech, and Signal Proc., 28 (2), 137 -145, 1980.
3. Mokbel, C., Mauuary, L., Karray, L., Jouvet, D., Monné, J., Simonin, J., and Bartkova, K., "Towards improving ASR robustness for PSN and GSM telephone applications", Speech Comm., 23, 141 -159, 1997.
4. Claes, T., Xie, F., and Van Compernolle, D, "Spectral estimation and normalisation for robust speech recognition", in: Proc. ICSLP-96, 1996.
5. Hilger, F., and Ney, H., "Noise level normalization and reference adaptation for robust speech recognition", in: Proc. ASR-2000, 64 -68, 2000.
6. Peeling, S.M., and Ponting, K.M., "Variable frame rate analysis in the ARM continuous speech recognition system", Speech Comm., 10, 155 -162, 1990.
7. Hirsch, G., and Pearce, D., "Second experimental framework for the performance evaluation of speech recognition front-ends", STQ Aurora DSR Working Group, document AU/231/00, 2000.
8. Knoblich, U., "Description and baseline results for the subset of the SpeechDat Car Italian database used for ETSI STQ Aurora WI008 advanced DSR front-end evaluation", STQ Aurora DSR Working Group, document AU/237/00, 2000.
9. Noe, B., Sienel, J., Jouvet, D., Mauuary, L., Boves, L., de Veth, J. and de Wet, F. "Noise reduction for noise robust feature extraction for distributed speech recognition", submitted to this conference.