Utterance Verification Using Word Voiceprint Models Based on Probabilistic Distributions of Phone-Level Log-Likelihood Ratio and Phone Duration

Suk-Bong KWON
HoiRin KIM

IEICE TRANSACTIONS on Information and Systems   Vol.E91-D    No.11    pp.2746-2750
Publication Date: 2008/11/01
Online ISSN: 1745-1361
DOI: 10.1093/ietisy/e91-d.11.2746
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Speech and Hearing
utterance verification,  confidence measure,  likelihood ratio testing,  word voiceprint,  

Full Text: PDF(181.7KB)>>
Buy this Article

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.

open access publishing via