Likelihood normalization for speaker verification using a phoneme- and speaker-independent model

Speech Communication

Volumn 17, Issue 1-2, 1995, Pages 109-116

  Matsui, Tomoko ^a   Furui, Sadaoki ^a  

^a NTT CORPORATION   (Japan)

Author keywords

A posteriori probability; Likelihood normalization; Phoneme and speaker independent model; Speaker verification

Indexed keywords

CALCULATIONS; MATHEMATICAL MODELS; PATTERN RECOGNITION SYSTEMS; PERFORMANCE; SPEECH COMMUNICATION; SYSTEMS ANALYSIS;

SIMILARITY NORMALIZATION; SPEAKER VERIFICATION; TEXT PROMPTED VERIFICATION;

SPEECH RECOGNITION;

EID: 0029355724     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/0167-6393(95)00011-C     Document Type: Article

References (9)

1. An inequality and associated maximization technique in statistical estimation for probabilistic functions of Markov process
2. Speaker verification using connected words
3. Limited parameter hidden Markov models for connected digit speaker verification over telephone channels
4. Speaker verification using randomized phrase prompting
5. Normalization and selection of speech segments for speaker recognition scoring
6. Comparison of text-independent speaker recognition methods using VQ-distortion and discrete/continuous HMMs
7. Concatenated phoneme models for text-variable speaker recognition
8. Speaker adaptation of tied-mixture-based phoneme models for text-prompted speaker recognition
9. The use of cohort normalized scores for speaker verification