Co-channel speaker separation based on maximum-likelihood deconvolution

Author

Savic, Michael ; Gao, Huiqin ; Sorensen, Jeffrey S.

Author_Institution

Dept. of Electr. Comput. & Syst. Eng., Rensselaer Polytech. Inst., Troy, NY, USA

Volume

i

fYear

1994

fDate

19-22 Apr 1994

Abstract

Described is a speaker separation system based on the maximum likelihood deconvolution (MLD). The maximum likelihood criteria is applied to the deconvolution of the combined signal to estimate the excitation signal of each speaker. Passing the estimated excitation signal through the corresponding vocal tract filter produces the restored speech of the particular speaker. The restored speech is the result of the convolution of the excitation signal with the vocal tract wavelet matrix. A simultaneous characterization of multiple speakers was accomplished with a new speech model

Keywords

deconvolution; filtering theory; maximum entropy methods; speech coding; speech enhancement; speech intelligibility; wavelet transforms; LPC; co-channel speaker separation; codebook; excitation signal; maximum-likelihood deconvolution; multiple speakers characterisation; restored speech; speech enhancement; speech intelligibility; speech model; vocal tract filter; vocal tract wavelet matrix; Backscatter; Convolution; Deconvolution; Equations; Filters; Interference; Maximum likelihood estimation; Signal restoration; Speech enhancement; Systems engineering and theory;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1994. ICASSP-94., 1994 IEEE International Conference on

Conference_Location

Adelaide, SA

ISSN

1520-6149

Print_ISBN

0-7803-1775-0

Type

conf

DOI

10.1109/ICASSP.1994.389364

Filename

389364