Speaker identification using Gaussian mixture models based on multi-space probability distribution

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 1, Issue , 2001, Pages 433-436

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

^a NAGOYA INSTITUTE OF TECHNOLOGY   (Japan)

^b TOKYO INSTITUTE OF TECHNOLOGY   (Japan)

^c DENSO CORPORATION   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

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

FEATURE EXTRACTION; MATHEMATICAL MODELS; MAXIMUM LIKELIHOOD ESTIMATION; PROBABILITY DISTRIBUTIONS; SPEECH ANALYSIS;

SPEECH RECOGNITION;

EID: 0034843062     PISSN: 15206149     EISSN: None     Source Type: Journal    
DOI: 10.1109/ICASSP.2001.940860     Document Type: Article

References (10)

1. Robust text-independent speaker identification using Gaussian mixture speaker models
2. Automatic speaker recognition based on pitch contours
3. Research on individuality features in speech waves and automatic speaker recognition techniques
4. Robust prosodic features for speaker identification
5. A lognormal tied mixture model of pitch for prosody-based speaker recognition
6. Text-independent speaker recognition using vocal tract and pitch information
7. Integrating pitch and LPC-residual information with LPC-cepstrum for text-independent speaker recognition
8. Hidden Markov models based on multi-space probability distribution for pitch pattern modeling
9. An adaptive algorithm for mel-cepstral analysis of speech
10. A robust algorithm for pitch tracking