Designing multiple distinctive phonetic feature extractors for canonicalization by using clustering technique
Designing multiple distinctive phonetic feature extractors for canonicalization by using clustering technique
复制标题
利用聚类技术设计多个独特的语音特征提取器进行规范化
DOI：
10.21437/interspeech.2005-268
复制
发表时间：
2005
期刊：
影响因子：
--
通讯作者：
T. Nitta
中科院分区：
文献类型：
--
作者：
Takashi Fukuda;Muhammad Ghulam;T. Nitta
基于隐马尔可夫模型的分类器的声学模型包括各种类型的隐藏因素，如说话人特定的特征和声学环境。如果存在一个规范化过程来抑制由于隐藏因素导致的类别间声学似然差异的减小，则可以实现稳健的ASR系统。我们已经提出了特征参数的规范化过程，该过程由三个专注于性别因素的不同语音特征(DPF)抽取器组成。本文描述了一种设计对应于非特定隐藏因素的多个DPF抽取器的尝试，以及引入一种针对噪声因素的规范化的噪声抑制器。在日文版AURORA2数据库(AURORA2-J)上的实验中，将归一化过程与基于两级维纳滤波的降噪技术相结合，该系统取得了显著的改进。
Acoustic models of an HMM-based classifier include various types of hidden factors such as speaker-specific characteristics and acoustic environments. If there exist a canonicalization process that represses the decrease of differences in acoustic-likelihood among categories resulted from hidden factors, a robust ASR system can be realized. We have previously proposed the canonicalization process of featureparameters composed of three distinctive phonetic feature (DPF) extractors focused on a gender factor. This paper describes an attempt to design multiple DPF extractors corresponding to unspecific hidden factors, as well as to introduce a noise suppressor that is targeted for the canonicalization of a noise factor. In an experiment on Japanese version AURORA2 database (AURORA2-J), the proposed system achieved significant improvements when combining the canonicalization process with the noise reduction technique based on a two-stage Wiener filter.
DOI：
10.1093/ietisy/e88-d.3.535
发表时间：
2005-03
期刊：
IEICE Trans. Inf. Syst.
影响因子：
--
作者：
Satoshi Nakamura;K. Takeda;Kazumasa Yamamoto;Takeshi Yamada;S. Kuroiwa;N. Kitaoka;T. Nishiura;A. Sasou;M. Mizumachi;C. Miyajima;Masakiyo Fujimoto;Toshiki Endo
通讯作者：
Satoshi Nakamura;K. Takeda;Kazumasa Yamamoto;Takeshi Yamada;S. Kuroiwa;N. Kitaoka;T. Nishiura;A. Sasou;M. Mizumachi;C. Miyajima;Masakiyo Fujimoto;Toshiki Endo
DOI：
--
发表时间：
2003
期刊：
--
影响因子：
--
作者：
Satoshi Nakamura;Kazumasa Yamamoto;K. Takeda;S. Kuroiwa;N. Kitaoka;Takeshi Yamada;M. Mizumachi;T. Nishiura;Masakiyo Fujimoto;A. Saso;Toshiki Endo
通讯作者：
Satoshi Nakamura;Kazumasa Yamamoto;K. Takeda;S. Kuroiwa;N. Kitaoka;Takeshi Yamada;M. Mizumachi;T. Nishiura;Masakiyo Fujimoto;A. Saso;Toshiki Endo