|
KMID : 0917520070140040145
|
|
Journal of Speech Sciences
2007 Volume.14 No. 4 p.145 ~ p.156
|
|
|
Speaker Identification Using Score-based Confidence in Noisy Environments
|
|
Min So-Hee
Song Min-Gyu
Na Seung-You
Choi Seung-Ho
Kim Jin-Young
|
|
|
Abstract
|
|
|
|
The performance of speaker identification is severely degraded in noisy environments. Recently probability weighting method based on observation membership was proposed for overcoming the noise problem[1]. In the paper[1] the observation confidence was calculated from SNR with sigmoid function. However, estimating SNR needs additive calculation amount and estimated SNR is corrupted in dynamic noisy environments. In this paper we propose estimation methods of the observation confidence based on score-based reliabilities (SBR) of entropy and dispersion measures. Generally SBRs are obtained from speaker models’ probabilities. The proposed methods are evaluated with ETRI speaker recognition DB. We compared the performances of the proposed methods with those in [1][8]. The experimental results show that the proposed methods can be successfully applied for the case where SNR is not available.
|
|
|
KEYWORD
|
|
|
Speaker identification, GMM, Score-based reliability, Observation Confidence
|
|
|
FullTexts / Linksout information
|
|
|
|
|
|
Listed journal information
|
|
|
|