Robust Speech Recognition Method Based on Discriminative Environment Feature Extraction

作     者：韩纪庆 高文 

作者机构：DepartmentofComputerScienceandEngineeringHarbinInstituteofTechnologyHarbin150001P.R.China InstituteofComputingTechnologyTheChineseAcademyofSciencesBeijing100080P.R.China 

出 版 物：《Journal of Computer Science & Technology》 (计算机科学技术学报（英文版）)

年 卷 期：2001年第16卷第5期

页      面：458-464页

核心收录：

学科分类：1305[艺术学-设计学（可授艺术学、工学学位）] 13[艺术学] 081104[工学-模式识别与智能系统] 08[工学] 0804[工学-仪器科学与技术] 081101[工学-控制理论与控制工程] 0811[工学-控制科学与工程] 

基　　金：the '863' High-Tech Programme of China (No. 863-306ZT03-02-3) and partially by the National Natural Science Foundation of China 

主　　题：robust speech recognition minimum classification error environmental parameter discriminative learning 

摘      要：It is an effective approach to learn the influence of environmental parameters, such as additive noise and channel distortions, from training data for robust speech recognition. Most of the previous methods are based on maximum likelihood estimation criterion. However, these methods do not lead to a minimum error rate result. In this paper, a novel discrimina-tive learning method of environmental parameters, which is based on Minimum Classification Error (MCE) criterion, is proposed. In the method, a simple classifier and the Generalized Probabilistic Descent (GPD) algorithm are adopted to iteratively learn the environmental pa-rameters. Consequently, the clean speech features are estimated from the noisy speech features with the estimated environmental parameters, and then the estimations of clean speech features are utilized in the back-end HMM classifier. Experiments show that the best error rate reduction of 32.1% is obtained, tested on a task of 18 isolated confusion Korean words, relative to a conventional HMM system.