Monaural voiced speech segregation based on elaborate harmonic grouping strategies  

作　　者：LIU WenJu ZHANG XueLiang JIANG Wei LI Peng XU Bo 

机构地区：[1]National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Bcijing 100190, China [2]Digital Media Content Technology Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China

出　　处：《Science China(Information Sciences)》2011年第12期2471-2480,共10页中国科学（信息科学）（英文版）

基　　金：supported by the National Natural Science Foundation of China(Grant Nos.60675026,90820303,90820011)

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.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.

关 键 词：computational auditory scene analysis voiced speech separation harmonistic principle minimum amplitude principle elaborate harmonic grouping strategies 

分 类 号：TN722.75[电子电信—电路与系统] TM864[电气工程—高电压与绝缘技术]