標題: | Discriminative training of Gaussian mixture bigram models with application to Chinese dialect identification |
作者: | Tsai, WH Chang, WW 電信工程研究所 Institute of Communications Engineering |
關鍵字: | Gaussian mixture bigram model;minimum classification error algorithm;Chinese dialect identification |
公開日期: | 1-三月-2002 |
摘要: | This study focuses on the parametric stochastic modeling of characteristic sound features that distinguish languages from one another. A new stochastic model. the so-called Gaussian mixture bigram model (GMBM), that allows exploitation of the acoustic feature bigram statistics without requiring transcribed training data is introduced. For greater efficiency, a minimum classification error (MCE) algorithm is employed to accomplish discriminative training of a GMBM-based Chinese dialect identification system. Simulation results demonstrate the effectiveness of the GMBM for dialect-specific acoustic modeling, and use of this model allows the proposed system to distinguish between the three major Chinese dialects spoken in Taiwan with 94.4% accuracy. (C) 2002 Elsevier Science B.V. All rights reserved. |
URI: | http://dx.doi.org/10.1016/S0167-6393(00)00090-X http://hdl.handle.net/11536/28962 |
ISSN: | 0167-6393 |
DOI: | 10.1016/S0167-6393(00)00090-X |
期刊: | SPEECH COMMUNICATION |
Volume: | 36 |
Issue: | 3-4 |
起始頁: | 317 |
結束頁: | 326 |
顯示於類別: | 期刊論文 |