Improved data modeling for text-dependent speaker recognition using sub-band processing

International Journal of Speech Technology

Volumn 4, Issue 1, 2001, Pages 45-62

  Finan, R A ^a   Damper, R I ^b   Sapeluk, A T ^a  

^a UNIVERSITY OF ABERTAY DUNDEE   (United Kingdom)

^b UNIVERSITY OF SOUTHAMPTON   (United Kingdom)

Author keywords

Bias variance dilemma; Fletcher Allen principle; Information fusion; Linear prediction; Speaker recognition

Indexed keywords

ERROR DETECTION; MATHEMATICAL MODELS; SPEECH PROCESSING; SPEECH SYNTHESIS; TIME DOMAIN ANALYSIS;

FLETCHER-ALLEN PRINCIPLE; SUB-BAND PROCESSING; TIME-DOMAIN SPEECH SIGNAL;

SPEECH RECOGNITION;

EID: 0035278987     PISSN: 13812416     EISSN: None     Source Type: Journal    
DOI: 10.1023/A:1009652732313     Document Type: Article

References (52)

1. How do humans process and recognize speech?
2. Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification
3. Equalizing sub-band error rates in speaker recognition
4. Subband approach for automatic speaker recognition: Optimal division of the frequency domain
5. Second-order statistical measures for text-independent speaker recognition
6. Enhancements to DTW and VQ decision algorithms for speaker recognition
7. A new ASR approach based on independent processing and recombination of partial frequency bands
8. Combining evidence from separate speech recognition processes
9. Speaker recognition: A tutorial
10. Speaker verification using connected words
11. Speaker recognition-Identifying people by their voices
12. Sheeps, goats, lambs and wolves: A statistical analysis of speaker performance in the NIST 1998 speaker recognition evaluation
13. Impostor cohort selection for score normalisation in speaker verification
14. Recent advances in speaker recognition
15. Theory of communication
16. Communication theory and physics
17. Neural networks and the bias/variance dilemma
18. Visionary speech: Looking ahead to practical speechreading systems
19. Should recognizers have ears?
20. RASTA processing of speech
21. TRAPS-Classifiers of temporal patterns
22. Towards ASR on partially corrupted speech
23. Adaptive mixtures of local experts
24. On combining classifiers
25. Normalizations and selection of speech segments for speaker recognition scoring
26. An algorithm for vector quantizer design
27. Likelihood normalization for speaker verification using phone- and speaker-independent models
28. The full-combination sub-bands approach to noise robust HMM/ANN-based ASR
29. Speaker verification over long-distance telephone lines
30. Multi-band speech recognition in noisy environments
31. Signal modeling techniques in speech recognition
32. Experimental evaluation of features for robust speaker identification
33. Speaker identification and verification using Gaussian mixture models
34. Comparison of background normalization methods for text-independent speaker verification
35. Speaker background models for connected digit password speaker verification
36. Evaluation of a vector quantization talker recognition system in text dependent and text independent modes
37. Sub-band speaker verification using dynamic recombination weights
38. An effective sub-band based approach for robust speaker verification
39. Mutual dependence of the octave-band weights in predicting speech intelligibility
40. The pre-detection of error-prone class members at the enrollment stage of speaker recognition systems
41. Sub-band based recognition of noisy speech
42. Stacked generalization
43. Speaker recognition using hidden Markov models, dynamic time warping and vector quantisation
44. Analytical expressions for critical-band rate and critical bandwidth as a function of frequency