AANN: An alternative to GMM for pattern recognition

Neural Networks

Volumn 15, Issue 3, 2002, Pages 459-469

  Yegnanarayana, B ^a   Kishore, S P ^a  

^a INDIAN INSTITUTE OF TECHNOLOGY MADRAS   (India)

Author keywords

Annealing gain parameter; Autoassociative neural network models; Speaker verification; Training error surface

Indexed keywords

MAPPING; MATHEMATICAL MODELS; PATTERN RECOGNITION; PROBLEM SOLVING;

GAUSSIAN MIXTURE MODELS;

NEURAL NETWORKS;

ARTICLE; ARTIFICIAL NEURAL NETWORK; DATA ANALYSIS; ERROR; NORMAL DISTRIBUTION; PATTERN RECOGNITION; PRIORITY JOURNAL; SPEECH; STATISTICAL MODEL; SURFACE PROPERTY; TRAINING; AUTOMATED PATTERN RECOGNITION;

NEURAL NETWORKS (COMPUTER); NORMAL DISTRIBUTION; PATTERN RECOGNITION; PATTERN RECOGNITION, AUTOMATED;

EID: 0035989168     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(02)00019-9     Document Type: Article

References (29)

1. Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification
2. Nonlinear dimensionality reduction
3. Maximum likelihood from incomplete data via the EM algorithm
4. Imposter cohort selection for score normalization in speaker verification
5. Cepstral analysis technique for automatic speaker verification
6. Autoassociator-based models for speaker verification
7. Vector quantization
8. Use of autoassociative neural networks for signal validation
9. Analysis of autoassociative mapping neural networks
10. Handwritten numerical recognition using autoassociative neural networks
11. Speaker verification: Minimizing the channel effect using autoassociative neural networks models
12. Nonlinear principal component analysis using autoassociative neural networks
13. An introduction to computing with neural nets
14. Linear prediction: A tutorial review
15. Speaker recognition workshop notebook
16. Speaker recognition workshop notebook
17. What's in a number? Moving beyond the equal error rate
18. Data compression, feature extraction and autoassociation in feedforward neural networks
19. Mixture densities, maximum likelihood and the EM algorithm
20. Comparison of background normalization methods for text-independent speaker verification
21. Schemata and sequential thought processes in PDP models
22. Neural networks models for capturing probability distribution of training data