Indexing telephone conversations by speakers using time-frequency principal component analysis

IEEE International Conference on Multi-Media and Expo

Volumn , Issue II/TUESDAY, 2000, Pages 881-884

  Magrin Chagnolleau, I ^a   Bimbot, F ^a  

^a INRIA   (France)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; INDEXING (OF INFORMATION); MATRIX ALGEBRA; PRINCIPAL COMPONENT ANALYSIS; STEREOPHONIC RECORDINGS; TELEPHONE TRAFFIC RECORDING; VECTORS;

SPEAKER TRACKING;

SPEECH ANALYSIS;

EID: 0034502151     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (15)

1. Approaches to speaker detection and tracking in multi-speaker audio
2. AMIRAL: A block-segmental multi-recognizer architecture for automatic speaker recognition
3. Comparison of speaker recognition methods using static features and dynamic features
4. Local normalization and delayed decision making in speaker detection and tracking
5. Time-frequency principal components of speech: Application to speaker identification
6. Application of time-frequency principal component analysis to speaker verification
7. Application of time-frequency principal component analysis to text-independent speaker identification
8. Detection of target speakers in audio databases
9. The DET curve in assessment of detection task performance
10. Homomorphic analysis of speech
11. Robust text-independent speaker identification using gaussian mixture speaker models
12. Speaker detection in broadcast speech databases
13. The IRISA / ELISA speaker detection and tracking systems for the NIST'99 evaluation campaign