Speaker identification and verification using Gaussian mixture speaker models

Speech Communication

Volumn 17, Issue 1-2, 1995, Pages 91-108

  Reynolds, Douglas A ^a  

^a MIT LINCOLN LABORATORY   (United States)

Author keywords

Automatic speaker identification and verification; Gaussian mixture speaker models; NTIMIT; Switchboard; Text independent; TIMIT; Vocabulary dependent; YOHO

Indexed keywords

BIT ERROR RATE; CONSTRAINT THEORY; DATABASE SYSTEMS; MATHEMATICAL MODELS; PATTERN RECOGNITION SYSTEMS; SPEECH COMMUNICATION; STATISTICAL METHODS;

GAUSSIAN MIXTURE SPEAKER MODELS; GLOBAL THRESHOLD EQUAL ERROR RATE; LIKELIHOOD RATIO HYPOTHESIS TESTER; MAXIMUM LIKELIHOOD CLASSIFIER; SPEAKER IDENTIFICATION SYSTEM; SPEAKER VERIFICATION; SWITCHBOARD DATABASE;

SPEECH RECOGNITION;

EID: 0029355999     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/0167-6393(95)00009-D     Document Type: Article

References (28)

1. Interactively skimming recorded speech
2. Improved voice identification using a nearest-neighbor distance measure
3. Features and measures for speaker recognition
4. Testing with the YOHO CD-ROM voice verification corpus
5. Maximum likelihood from incomplete data via the EM algorithm
6. Speaker recognition-identifying people by their voices
7. The DARPA speech recognition research database: Specifications and status
8. Investigations on speaker characterization from Orphee system technics
9. Application of large vocabulary continuous speech recognition to topic and speaker identification using telephone speech
10. Text-independent speaker identification
11. Switchboard: Telephone speech corpus for research and development
12. Speaker verification using randomized phrase prompting
13. Voice identification using nearest-neighbor distance measure
14. NTIMIT A phonetically balanced continuous speech telephone bandwidth speech database
15. A subword neural tree network approach to text-dependent speaker verification
16. Evaluation of a high performance speaker verification system for access control
17. Speaker verification over long distance telephone lines
18. A Gaussian mixture modeling approach to text-independent speaker identification
19. PC-based TMS320C30 implementation of the Gaussian mixture model text-independent speaker recognition system
20. Effects of population size and telephone degradations on speaker identification performance
21. Experimental evaluation of features for robust speaker identification
22. The effects of telephone transmission degradations on speaker recognition performance
23. Robust text-independent speaker identification using Gaussian mixture speaker models
24. Text-independent speaker identification using automatic acoustic segmentation
25. The use of cohort normalized scores for speaker verification
26. A conversational telephone messaging system
27. Segmentation of speech using speaker identification