標題: A Reference Model Weighting-based Method for Robust Speech Recognition
作者: Liao, Yuan Fu
Yang, Yh-Her
Hsu, Chi-Hui
Lee, Cheng-Chang
Zeng, Jing-Teng
電信工程研究所
Institute of Communications Engineering
公開日期: 1-Jan-2007
摘要: In this paper a reference model weighting (RMW) method is proposed for fast hidden Markov model (HMM) adaptation which aims to use only one input test utterance to online estimate the characteristic of the unknown test noisy environment. The idea of RMW is to first collect a set of reference HMMs in the training phase to represent the space of noisy environments, and then synthesize a suitable HMM for the unknown test noisy environment by interpolating the set of reference HMMs. Noisy environment mismatch can hence be efficiently compensated. The proposed method was evaluated on the multi-condition training task of Aurora2 corpus. Experimental results showed that the proposed RMW approach outperformed both the histogram equalization (HEQ) method and the distributed speech recognition (DSR) standard ES 202 212 proposed by European Telecommunications Standards Institute (ETSI).
URI: http://hdl.handle.net/11536/146253
期刊: INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4
起始頁: 2916
Appears in Collections:Conferences Paper