A LOGNORMAL TIED MIXTURE MODEL OF PITCH FOR PROSODY-BASED SPEAKER RECOGNITION

5th European Conference on Speech Communication and Technology, EUROSPEECH 1997

Volumn , Issue , 1997, Pages 1391-1394

  Sönmez, M Kemal ^a   Heck, Larry ^a   Weintraub, Mitchel ^a   Shriberg, Elizabeth ^a  

^a SRI INTERNATIONAL   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

CODES (SYMBOLS); ERRORS; IMAGE RESOLUTION; MIXTURES; NORMAL DISTRIBUTION; SPEECH COMMUNICATION; SPEECH RECOGNITION;

% REDUCTIONS; DOUBLINGS; FALSE ALARM RATE; LOG-NORMAL; LOG-NORMAL DISTRIBUTION; MISS-RATE; MIXTURE MODELING; SPEAKER RECOGNITION; SPEAKER RECOGNITION SYSTEM; TIED-MIXTURES;

STATISTICS;

EID: 85135139722     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (4)

1. M.J. Carey, E.S. Parris, H. Lloyd-Thomas, and S. Bennett. "Robust prosodic features for speaker identification". In NIST Speaker Recognition Workshop, March 1996.
2. B. F. Necioğlu, M. A. Clements, and T. P. Barnwell III. "Reliability assessment and evaluation of objectively measured descriptors for perceptual speaker characterization". In ICASSP, May 1997.
3. M. Weintraub. A Theory and Computational Model of Auditory Monaural Sound Separation. PhD thesis, Stanford University, 1985.
4. Johnson N. L., Kotz S., and N. Balakrishnan. Continuous Univariate Distributions: Volume 1. Wiley, 1994.