Text-independent speaker identification using Gaussian mixture models based on multi-space probability distribution

IEICE Transactions on Information and Systems

Volumn E84-D, Issue 7, 2001, Pages 847-855

  Miyajima, Chiyomi ^a   Hattori, Yosuke ^a,b   Tokuda, Keiichi ^a   Masuko, Takashi ^c   Kobayashi, Takao ^c   Kitamura, Tadashi ^c  

^a NAGOYA INSTITUTE OF TECHNOLOGY   (Japan)

^b DENSO CORPORATION   (Japan)

^c TOKYO INSTITUTE OF TECHNOLOGY   (Japan)

Author keywords

Gaussian mixture model; Minimum classification error; Multi space probability distribution; Pitch; Speaker identification

Indexed keywords

ERROR ANALYSIS; MATHEMATICAL MODELS; MAXIMUM LIKELIHOOD ESTIMATION; PROBABILITY DISTRIBUTIONS;

GAUSSIAN MIXTURE MODELS; MINIMUM CLASSIFICATION ERROR; MULTI-SPACE PROBABILITY DISTRIBUTION; TEXT-INDEPENDENT SPEAKER IDENTIFICATION;

SPEECH RECOGNITION;

EID: 0035394386     PISSN: 09168532     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (23)

1. Robust text-independent speaker identification using Gaussian mixture speaker models
2. A vector quantization approach to speaker recognition
3. Automatic speaker recognition based on pitch contours
4. Research on individuality features in speech waves and automatic speaker recognition techniques
5. Robust prosodic features for speaker identification
6. A lognormal tied mixture model of pitch for prosody-based speaker recognition
7. Text-independent speaker recognition using vocal tract and pitch information
8. Integrating pitch and LPC-residual information with LPC-cepstrum for text-independent speaker recognition
9. Hidden Markov models based on multi-space probability distribution for pitch pattern modeling
10. Multi-space probability distribution HMM
11. Speaker identification using Gaussian mixture based on multi-space probability distribution
12. Discriminative learning for minimum error classification
13. Pattern recognition using a family of design algorithms based upon the generalized probabilistic descent method
14. A study on minimum error discriminative training for speaker recognition
15. Discriminative training of GMM for speaker identification
16. Speaker verification using minimum verification error training
17. Speaker identification using minimum classification error training
18. Construction of ATR Japanese speech database as a research tool (Appendix II)
19. Comparison of text-independent speaker recognition methods using VQ-distortion and discrete/continuous HMMs
20. An adaptive algorithm for Mel-Cepstral analysis of speech
21. A robust algorithm for pitch tracking
22. Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification
23. Cepstral analysis technique for automatic speaker verification