On-line incremental speaker adaptation with automatic speaker change detection

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

Volumn 2, Issue , 2000, Pages 961-964

  Zhang, Zhi Peng ^a   Furui, Sadaoki ^a   Ohtsuki, Katsutoshi ^b  

^a TOKYO INSTITUTE OF TECHNOLOGY   (Japan)

^b NTT CORPORATION   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

ONLINE SYSTEMS; SIGNAL PROCESSING; BROADCASTING; ERROR ANALYSIS; FEATURE EXTRACTION; MARKOV PROCESSES; MATHEMATICAL MODELS; MATHEMATICAL TRANSFORMATIONS; MAXIMUM LIKELIHOOD ESTIMATION; REGRESSION ANALYSIS; SPEECH ANALYSIS; VECTORS;

ADAPTIVE GAUSSIAN MIXTURE MODELS; AUTOMATIC DETECTION; BROADCAST NEWS TRANSCRIPTIONS; CONVENTIONAL METHODS; SPEAKER ADAPTATION; SPEAKER CHANGE DETECTION; SPEAKER INDEPENDENTS; SPEECH RECOGNITION SYSTEMS;

SPEECH RECOGNITION;

GAUSSIAN MIXTURE MODELS; HIDDEN MARKOV MODELS; MAXIMUM LIKELIHOOD LINEAR REGRESSION TRANSFORMATION; SPEAKER ADAPTATION;

EID: 0033708392     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2000.859121     Document Type: Conference Paper

References (5)

1. K. Ohtsuki, et al., "Improvements in Japanese broadcast news transcription," Proc. DARPA Broadcast News Workshop, pp. 231-236, 1999.
2. K. Ohtsuki, et al., "Recent advances in Japanese broadcast news transcription," Proc. Eurospeech'99, pp. 671-674, 1999.
3. C. J. Leggetter, et al., "Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models," Computer Speech and Language, pp. 171-185, 1995.
4. K. Ohkura, et al., "Speaker adaptation based on transfer vector field smoothing with continuous mixture density HMMs," Proc. ICSLP'92, pp. 369-372, 1992.
5. T. Hain, et al., "Segment generation and clustering in the HTK broadcast news transcription system," Proc. DARPA Broadcast News Transcription and Understanding Workshop, pp. 133-137, 1998.