Monaural voiced speech segregation based on elaborate harmonic grouping strategies

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 voiced speech segregation based on elaborate harmonic grouping strategies
	Liu WenJu1 ; Zhang XueLiang 1; Jiang Wei 1; Li Peng2 ; Xu Bo2
刊名	SCIENCE CHINA-INFORMATION SCIENCES
	2011-12-01
卷号	54 期号:12 页码:2471-2480
关键词	computational auditory scene analysis voiced speech separation harmonistic principle minimum amplitude principle elaborate harmonic grouping strategies
英文摘要	In this paper, an enhanced algorithm based on several elaborate harmonic grouping strategies for monaural voiced speech segregation is proposed. Main achievements of the proposed algorithm lie in three aspects. Firstly, the algorithm classifies the time-frequency (T-F) units into resolved and unresolved ones by carrier-to-envelope energy ratio, which leads to more accurate classification results than by cross-channel correlation. Secondly, resolved T-F units are grouped together according to minimum amplitude principle, which has been verified to exist in human perception, as well as the harmonic principle. Finally, "enhanced" envelope autocorrelation function is employed to detect amplitude modulation rates, which helps a lot in reducing half-frequency error in grouping of unresolved units. Systematic evaluation and comparison show that performance of separation is greatly improved by the proposed algorithm. Specifically, signal-to-noise ratio (SNR) is improved by 0.96 dB compared with that of previous method. Besides, our algorithm is also effective in improving the PESQ score and subjective perception score.
WOS标题词	Science & Technology ; Technology
类目[WOS]	Computer Science, Information Systems
研究领域[WOS]	Computer Science
关键词[WOS]	BLIND SEPARATION ; MODULATION
收录类别	SCI
语种	英语
WOS记录号	WOS:000297709400003
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/3301]
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, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Inst Automat, Digital Media Content Technol Res Ctr, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Liu WenJu,Zhang XueLiang,Jiang Wei,et al. Monaural voiced speech segregation based on elaborate harmonic grouping strategies[J]. SCIENCE CHINA-INFORMATION SCIENCES,2011,54(12):2471-2480.
APA	Liu WenJu,Zhang XueLiang,Jiang Wei,Li Peng,&Xu Bo.(2011).Monaural voiced speech segregation based on elaborate harmonic grouping strategies.SCIENCE CHINA-INFORMATION SCIENCES,54(12),2471-2480.
MLA	Liu WenJu,et al."Monaural voiced speech segregation based on elaborate harmonic grouping strategies".SCIENCE CHINA-INFORMATION SCIENCES 54.12(2011):2471-2480.