计算机工程Issue(5)：262-265,4.DOI:10.3969/j.issn.1000-3428.2014.05.054
基于语音识别与特征的无监督语音模式提取
Unsupervised Speech Pattern Extraction Based on Speech Recognition and Feature
摘要
Abstract
This paper proposes the unsupervised method based on both speech recognition system and feature-based system to search for the speech patterns. In speech recognition system, the alternative results of the speech recognition system decoder are used to search audio patterns with segmental dynamic time warping algorithm. Then graph clustering algorithm is used, as well as confidence estimation algorithm, to improve the performance of the system. It also proposes the system based on feature only without any knowledge resource. In the final, the performances of the two systems on both radio and television news and spoken dialogue sets are compared. The speech recognition system achieves better performance, and the feature based system can be used on many languages.关键词
语音识别/语音模式发现/分段动态时间弯曲算法/图聚类算法/音素回环后验概率计算Key words
speech recognition/speech pattern discovery/segmental dynamic time warping algorithm/graph clustering algorithm/phoneme loop calculation of posterior probability分类
信息技术与安全科学引用本文复制引用
张震,赵庆卫,颜永红..基于语音识别与特征的无监督语音模式提取[J].计算机工程,2014,(5):262-265,4.基金项目
国家自然科学基金资助项目(10925419,90920302,61072124,11074275,11161140319,91120001,61271426)；国家“863”计划基金资助项目(2012AA012503)；中国科学院重点部署基金资助项目(KGZD-EW-103-2)；中国科学院战略性先导科技专项基金资助项目“面向感知中国的新一代信息技术研究”(XDA06030100, XDA06030500)。 （10925419,90920302,61072124,11074275,11161140319,91120001,61271426）
