Monaural speech separation based on MAXVQ and CASA for robust speech recognition

CORC > 自动化研究所 > 中国科学院自动化研究所 > 数字内容技术与服务研究中心 > 听觉模型与认知计算

	Monaural speech separation based on MAXVQ and CASA for robust speech recognition
	Li, Peng1 ; Guan, Yong 2; Wang, Shijin 1; Xu, Bo1,2 ; Liu, Wenju2
刊名	COMPUTER SPEECH AND LANGUAGE
	2010
卷号	24 期号:1 页码:30-44
关键词	Monaural speech separation Computational auditory scene analysis (CASA) Factorial-max vector quantization (MAXVQ) Automatic speech recognition (ASR)
英文摘要	Robustness is one of the most important topics for automatic speech recognition (ASR) in practical applications. Monaural speech separation based on computational auditory scene analysis (CASA) offers a solution to this problem. In this paper, a novel system is presented to separate the monaural speech of two talkers. Gaussian mixture models (GMMs) and vector quantizers (VQs) are used to learn the grouping cues on isolated clean data for each speaker. Given an utterance, speaker identification is firstly performed to identify the two speakers presented in the utterance, then the factorial-max vector quantization model (MAXVQ) is used to infer the mask signals and finally the utterance of the target speaker is resynthesized in the CASA framework. Recognition results on the 2006 speech separation challenge corpus prove that this proposed system can improve the robustness of ASR significantly. (C) 2008 Elsevier Ltd. All rights reserved.
WOS标题词	Science & Technology ; Technology
类目[WOS]	Computer Science, Artificial Intelligence
研究领域[WOS]	Computer Science
关键词[WOS]	AUDITORY SCENE ANALYSIS ; MAXIMUM-LIKELIHOOD-ESTIMATION ; HIDDEN MARKOV-MODELS ; BIAS REMOVAL ; NOISE ; ADAPTATION
收录类别	SCI
语种	英语
WOS记录号	WOS:000270630700003
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/3299]
专题	数字内容技术与服务研究中心_听觉模型与认知计算
作者单位	1.Chinese Acad Sci, Inst Automat, Digital Content Technol Res Ctr, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Li, Peng,Guan, Yong,Wang, Shijin,et al. Monaural speech separation based on MAXVQ and CASA for robust speech recognition[J]. COMPUTER SPEECH AND LANGUAGE,2010,24(1):30-44.
APA	Li, Peng,Guan, Yong,Wang, Shijin,Xu, Bo,&Liu, Wenju.(2010).Monaural speech separation based on MAXVQ and CASA for robust speech recognition.COMPUTER SPEECH AND LANGUAGE,24(1),30-44.
MLA	Li, Peng,et al."Monaural speech separation based on MAXVQ and CASA for robust speech recognition".COMPUTER SPEECH AND LANGUAGE 24.1(2010):30-44.