Monaural voiced speech segregation based on elaborate harmonic grouping strategy

Author

Zhang, Xueliang ; Liu, Wenju ; Li, Peng ; Xu, Bo

Author_Institution

Nat. Lab. of Pattern Recognition (NLPR), Chinese Acad. of Sci., Beijing

fYear

2009

fDate

19-24 April 2009

Firstpage

4661

Lastpage

4664

Abstract

Monaural speech segregation is a very challenging problem which has been studied by many researchers. In this paper, we focus on voiced speech segregation. Different strategies are used to segregate resolved and unresolved harmonics respectively. For resolved harmonics, "harmonicity" principle and a novel mechanism based on "minimum amplitude" principle are employed. Amplitude modulation rate is extracted by "enhanced" autocorrelation function of envelope to segregate unresolved harmonics which is more robust than previous method. An elaborate rule is also introduced to determine the regions dominated by resolved and by unresolved harmonics. Proposed algorithm is evaluated on Cooke\´s 100 mixtures and compared with a state-of-the-art algorithm Hu and Wang model. Results show that proposed algorithm is more robust than the Hu and Wang model.

Keywords

speech processing; amplitude modulation rate; computational auditory scene analysis; elaborate harmonic grouping strategy; monaural voiced speech segregation; speech processing; Acoustic noise; Amplitude modulation; Autocorrelation; Humans; Image analysis; Noise robustness; Psychoacoustic models; Speech; Telecommunication computing; Working environment noise; Computational auditory scene analysis; Monaural speech separation; Speech processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on

Conference_Location

Taipei

ISSN

1520-6149

Print_ISBN

978-1-4244-2353-8

Electronic_ISBN

1520-6149

Type

conf

DOI

10.1109/ICASSP.2009.4960670

Filename

4960670