Speaker change detection and speaker clustering using VQ distortion for broadcast news speech recognition

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

Volumn 1, Issue , 2001, Pages 413-416

  Mori, K ^a   Nakagawa, S ^a  

^a TOYOHASHI UNIVERSITY OF TECHNOLOGY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

BAYESIAN INFORMATION CRITERION; GENERALIZED LIKELIHOOD RATIO; SPEAKER CLUSTERING; SPEAKER DETECTION;

ALGORITHMS; MATHEMATICAL MODELS; SPEECH ANALYSIS; SPEECH PROCESSING; STATISTICAL METHODS; VECTOR QUANTIZATION;

SPEECH RECOGNITION;

EID: 0034857759     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. A speaker tracking system based on speaker turn detection for NIST evaluation
2. Detection of speaker changes in an audio document
3. Speaker, environment and channel change detection and clustering via the bayesian information criterion
4. Unsupervised audio stream segmentation and clustering via the bayesian information criterion
5. Clustering speakers by their voices
6. Partitioning and transcription of broadcast news data
7. Text-independent speaker recognition using non-linear frame likelihood transformation
8. A new speech recognition method based on VQ-distortion measure and HMM
9. Evaluation of segmental unit input HMM
10. Blind clustering of speech utterance based on speaker and language characteristics
11. Acoustic back-off in the local distance computation for robust automatic speech recognition