Copyright © 2008 The Institute of Electronics, Information and Communication Engineers
Regular Section -- Letters -- Speech and Hearing |
Utterance Verification Using Word Voiceprint Models Based on Probabilistic Distributions of Phone-Level Log-Likelihood Ratio and Phone Duration
1 The authors are with Information and Communications University, Daejeon, Korea. E-mail: sbkwon{at}icu.ac.kr
 |
Abstract |
|---|
This paper suggests word voiceprint models to verify the recognition results obtained from a speech recognition system. Word voiceprint models have word-dependent information based on the distributions of phone-level log-likelihood ratio and duration. Thus, we can obtain a more reliable confidence score for a recognized word by using its word voiceprint models that represent the more proper characteristics of utterance verification for the word. Additionally, when obtaining a log-likelihood ratio-based word voiceprint score, this paper proposes a new log-scale normalization function using the distribution of the phone-level log-likelihood ratio, instead of the sigmoid function widely used in obtaining a phone-level log-likelihood ratio. This function plays a role of emphasizing a mis-recognized phone in a word. This individual information of a word is used to help achieve a more discriminative score against out-of-vocabulary words. The proposed method requires additional memory, but it shows that the relative reduction in equal error rate is 16.9% compared to the baseline system using simple phone log-likelihood ratios.
Key Words: utterance verification, confidence measure, likelihood ratio testing, word voiceprint
Manuscript received February 29, 2008. Manuscript revised June 17, 2008.