A blind separation algorithm of speech signal based on spatial cues

Author

Zhang, Xia ; Chang, Di ; Guo, Wei ; Yang, Wanyi ; Huang, Qian

Author_Institution

Sch. Phys. & Inf. Eng., Jianghan Univ., Wuhan, China

fYear

2011

fDate

26-28 July 2011

Firstpage

3319

Lastpage

3322

Abstract

Based on spatial cues, a blind separation algorithm of speech signal was proposed. In time-frequency domain, extract the spatial cues of speech signal, which are ITD and ILD, then construct the 2D diagram by distribution density of ITD and ILD. Next, mark the time-frequency binary masking and using this technique separate the source in time-frequency domain. Finally, I-STFT is used to transform the separated source back to time domain, and realize the blind separation algorithm of speech signal. To summarize, the proposed algorithm will give a new prospect to the research filed of blind separation of speech.

Keywords

blind source separation; speech processing; time-frequency analysis; 2D diagram construction; I-STFT transform; ILD distribution density; ITD distribution density; blind separation algorithm; interaural level difference distribution density; interaural time difference distribution density; spatial cue extraction; speech signal; time-frequency binary masking; time-frequency domain; Blind source separation; Europe; Software algorithms; Speech; Time frequency analysis; Blind Separation; Spatial Cues; W-disjoint orthogonal;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia Technology (ICMT), 2011 International Conference on

Conference_Location

Hangzhou

Print_ISBN

978-1-61284-771-9

Type

conf

DOI

10.1109/ICMT.2011.6002132

Filename

6002132