Speaker indexing in large audio databases using anchor models

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

Volumn 1, Issue , 2001, Pages 429-432

  Sturim, D E ^a   Reynolds, D A ^a   Singer, E ^a   Campbell, J P ^a  

^a MIT LINCOLN LABORATORY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

GAUSSIAN MIXTURE MODEL; HIDDEN MARKOV MODEL; SPEAKER DETECTION; UNIVERSAL BACKGROUND MODEL;

ALGORITHMS; DATABASE SYSTEMS; INFORMATION RETRIEVAL; MATHEMATICAL MODELS; PROBABILITY; SPEECH RECOGNITION; VECTORS;

SPEECH PROCESSING;

EID: 0034855361     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. Non directly acoustic process for costless speaker recognition and indexation
2. Speaker verification using adapted gaussian mixture models
3. Score normalization for text-independent speaker verification systems
4. Comparison of background normalization methods for text-independent speaker verification
5. The effects of handset variability on speaker recognition performance: Experiments on the switchboard corpus