Language model accuracy and uncertainty in noise cancelling in the stochastic weighted Viterbi algorithm

EUROSPEECH 2003 - 8th European Conference on Speech Communication and Technology

Volumn , Issue , 2003, Pages 2193-2196

  Yoma, Nestor Becerra ^a   Brito, Iván ^a   Silva, Jorge ^a  

^a UNIVERSITY OF CHILE   (Chile)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC NOISE; COMPUTATIONAL LINGUISTICS; DECODING; MODELING LANGUAGES; SPEECH; SPEECH COMMUNICATION; SPEECH RECOGNITION; STOCHASTIC MODELS; STOCHASTIC SYSTEMS; VITERBI ALGORITHM;

NOISE CANCELING; NOISE CANCELLING; NOISE ROBUSTNESS; PHONETIC LEVEL; ROUGH ESTIMATION; SPECTRAL SUBTRACTIONS; VITERBI DECODING; WORD ERROR RATE;

ADDITIVE NOISE;

EID: 85009204337     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (9)

1. Gales, M.J.F. and Young, S.J. (1993). HMM recognition in noise using parallel model combination.Proc. Eurospeech93, pp. 837-840, 1993.
2. Hermansky, H. et al. (1991). Compensation for the effect of the communication chennel in auditory-like analysis of speech (RASTA-PLP). Proc. Eurospeech 91, pp.1367-1370, 1991.
3. Hirsch, H.G., Pearce, D. (2000). The Aurora experimental framework for the performance evaluations of speech recognition systems under noisy conditions. ISCA ITRW ASR 2000, Paris, France, 2000.
4. Vaseghi, S.V. and Milner, B.P. (1997). Noise compensation methods for Hidden Markov Model speech recognition in adverse environments. IEEE Trans. on Speech and Audio Processing, 5 (1): 11-21, 1997.
5. Yoma, N.B., McInnes, F., Jack, M (1997). Weighted Matching Algorithms and Reliability in Noise Canceling by Spectral Subtraction. Proc. ICASSP 97, vol.2, pp. 1171-1174.
6. Yoma, N.B. et al. (1998). Improving performance of spectral subtraction in speech recognition using a model for additive noise. IEEE Trans. on Speech and Audio Processing, Vol. 6, No.6, pp. 579-582 November, 1998.
7. Yoma, N.B., Villar, M. (2001). Additive and convolutional noise canceling in speaker verification using a stochastic weighted Viterbi algorithm. Proc. Eurospeech 2001.
8. Yoma, N.B., Villar, M. (2002). Speaker verification in noise using a stochastic version of the weighted Viterbi algorithm. IEEE Trans. on Speech and Audio Processing, Vol. 10, No.3, pp. 158-166, 2002.
9. Yoma, N.B., Brito, I., Silva, J. (2002). The stochastic weighted Viterbi algorithm: on integrating language modelling and noise cancelling in speech recognition. Submitted to IEEE on SAP, October, 2000.