Speaker verification in noise using a stochastic version of the weighted Viterbi algorithm

IEEE Transactions on Speech and Audio Processing

Volumn 10, Issue 3, 2002, Pages 158-166

  Yoma, Néstor Becerra ^a,b   Villar, Miguel ^b  

^a IEEE   (Chile)

^b UNIVERSITY OF CHILE   (Chile)

Author keywords

Hidden Markov model (HMM); Noise robustness; Speaker verification; Viterbi algorithm

Indexed keywords

SPEAKER VERIFICATION;

ALGORITHMS; ERROR ANALYSIS; MARKOV PROCESSES; NOISE ABATEMENT; PROBABILITY; RANDOM PROCESSES; SPURIOUS SIGNAL NOISE;

SPEECH RECOGNITION;

EID: 0036508276     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSA.2002.1001980     Document Type: Article

References (23)

1. Robust speaker identification using multimicrophone systems
2. Enhancement of speech corrupted by acoustic noise
3. Speaker verification using connected words
4. Speaker verification in noisy environments with combined spectral subtraction and missing feature theory
5. Cepstral analysis technique for automatic speaker verication
6. Recent advances in speaker recognition
7. HMM recognition in noise using parallel model combination
8. 'Nice' model-based compensation schemes for robust speech recognition
9. Robustness against noise: The role of timing-synchrony measurement
10. Some statistical issues in the comparison of speech recognition algorithms
11. Spectral subtraction and RASTA-filtering in text-dependent HMM-based speaker verification
12. Compensation for the effect of the communication chennel in auditory-like analysis of speech (RASTA-PLP)
13. Providing single and multi-channel acoustical robustness in speaker identification systems
14. Experimental evaluation of features for robust speaker identification
15. Integrated models of signal and background with application to speaker identification in noise
16. Comparison of text-independent speaker recognition methods on telephone speech with acoustic mismatch
17. Noise compensation methods for hidden Markov model speech recognition in adverse environments
18. Weighted Viterbi algorithm and state duration modeling for speech recognition in noise
19. Improving performance of spectral subtraction in speech recognition using a model for additive noise