Speaker recognition - General classifier approaches and data fusion methods

Pattern Recognition

Volumn 35, Issue 12, 2002, Pages 2801-2821

  Ramachandran, Ravi P ^a   Farrell, Kevin R ^b   Ramachandran, Roopashri ^a   Mammone, Richard J ^c  

^a Rowan University   (United States)

^b T NETIX/SpeakEZ Inc   (United States)

^c RUTGERS UNIVERSITY   (United States)

Author keywords

Classifier; Diversity; Feature; Fusion; Redundancy; Robust; Speaker model; Speaker recognition; Supervised; Unsupervised

Indexed keywords

SECURITY SYSTEMS; SPEECH; TELEPHONE SETS;

BANK TRANSACTIONS;

PATTERN RECOGNITION;

ACOUSTIC DATA; PATTERN RECOGNITION;

EID: 0036887596     PISSN: 00313203     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0031-3203(01)00235-7     Document Type: Article

References (96)

1. Automatic recognition of speakers from their voices
2. Speaker recognition - Identifying people by their voices
3. Automatic speaker verification: A review
4. Recent research in automatic speaker recognition
5. Speaker recognition: A tutorial
6. Speaker recognition
7. Robust speaker recognition - A feature based approach
8. Suppression of acoustic noise in speech using spectral subtraction
9. Robust speaker identification using pole filtering
10. Channel and noise normalization using affine transformed cepstrum
11. Signal bias removal by maximum likelihood estimation for robust telephone speech recognition
12. A maximum-likelihood approach to stochastic matching for robust speech recognition
13. Probabilistic optimum filtering for robust speech recognition
14. Robust mapping of noisy speech parameters for HMM word spotting
15. A family of distortion measures based upon projection operation for robust speech recognition
16. Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification
17. New LP-derived features for speaker identification
18. Speaker identification based on the use of robust cepstral features obtained from pole-zero transfer functions
19. Text-independent speaker identification
20. A TMS32020 based real time, text-independent, automatic speaker verification system
21. Discriminant adaptive nearest neighbor classification
22. Speaker recognition using neural networks and conventional classifiers
23. Voice identification using nearest neighbor distance measure
24. Improved voice identification using a nearest neighbor distance measure
25. Vector quantization in speech coding
26. An algorithm for vector quantizer design
27. The self-organizing map
28. A discriminative training algorithm for VQ-based speaker identification
29. A vector quantization approach to speaker recognition
30. Evaluation of a vector quantization talker recognition system in text independent and text dependent modes
31. Speaker verification using randomized phrase prompting
32. The use of cohort normalized scores for speaker recognition
33. Robust text-independent speaker identification using Gaussian mixture speaker models
34. Speaker identification and verification using Gaussian mixture speaker models
35. Maximum likelihood from incomplete data via the EM algorithm
36. The expectation-maximization algorithm
37. Comparison of background normalization methods for text-independent speaker verification
38. The effects of telephone transmission degradations on speaker recognition performance
39. The effects of handset variability on speaker recognition performance: Experiments on the switchboard corpus
40. Integrated models of signal and background with application to speaker identification in noise
41. Cepstral analysis technique for automatic speaker verification
42. Minimum prediction residual principle applied to speech recognition
43. Dynamic programming algorithm optimization for spoken word recognition
44. A modified K-means clustering algorithm for use in isolated word recognition
45. Discriminative template training for dynamic programming speech recognition
46. A tutorial on hidden Markov models and selected applications in speech recognition
47. Continuous speech recognition using hidden Markov models
48. Comparison of text-independent speaker recognition methods using VQ distortion and discrete/continuous HMMs
49. Concatenated phoneme models for text-variable speaker recognition
50. Robust methods of updating model and a priori threshold in speaker verification
51. Background model design for flexible and portable speaker verification systems
52. Speaker verification over long distance telephone lines
53. Optimization of neural models for speaker identification
54. A connectionist approach for speaker identification
55. Radial basis function networks for speaker recognition
56. On the use of TDNN-extracted features information in talker identification
57. Text-dependent speaker verification using data fusion
58. A subword neural tree network approach to text-dependent speaker verification
59. Review of neural networks for speech recognition
60. Multivariable functional interpolation and adaptive networks
61. Phoneme recognition with time delay neural networks
62. Induction of decision trees
63. A performance comparison of trained multilayer perceptrons and trained classification trees
64. Growing and pruning neural tree networks
65. Sub-word speaker verification using data fusion methods
66. Estimation of error rates in discriminant analysis
67. On the use of instantaneous and transitional spectral information in speaker recognition
68. An analysis of data fusion methods for speaker verification
69. Neural tree network/vector quantization probability estimators for speaker recognition
70. Speaker verification with low storage requirements
71. Subword-based text-dependent speaker verification system with user-selectable passwords
72. Model combination and weight selection for speaker verification
73. Consensus theoretic classification methods
74. Methods of combining multiple classifiers and their applications to hand-written character recognition
75. Decision combination in multiple classifier systems
76. An analysis of four uncertainty calculi
77. Multiple classifier fusion for handwritten word recognition
78. Fusion of classifiers with fuzzy integrals
79. Information fusion by fuzzy integral
80. Fusion of handwritten numeral classifiers based on fuzzy and genetic algorithms
81. Fuzzy integration of classification results
82. Combining multiple neural networks by fuzzy integral for robust classification
83. Information fusion in computer vision using the fuzzy integral
84. Blind speech segmentation: Automatic segmentation of speech without linguistic knowledge