Robust speech recognition method based on discriminative environment feature extraction |
| |
| Authors: | Jiqing Han Wen Gao |
| |
| Affiliation: | (1) Department of Computer Science and Engineering, Harbin Institute of Technology, 150001 Harbin, P.R. China;(2) Institute of Computing Technology, The Chinese Academy of Sciences, 100080 Beijing, P.R. China |
| |
| Abstract: | 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. |
| |
| Keywords: | robust speech recognition minimum classification error environmental parameter discriminative learning |
| 本文献已被 CNKI 维普 万方数据 SpringerLink 等数据库收录！ |
|
