Semi-blind algorithm for joint noise suppression and dereverberation based on higher-order statistics and acoustic model likelihood

Author

Aprilyanti, Fine D. ; Saruwatari, Hiroshi ; Shikano, Kiyohiro ; Nakamura, Shigenari ; Takatani, Tomoya

Author_Institution

Grad. Sch. of Inf. Sci., Nara Inst. of Sci. & Technol., Nara, Japan

fYear

2013

fDate

Oct. 29 2013-Nov. 1 2013

Firstpage

1

Lastpage

6

Abstract

In this paper, we propose an automatic optimization scheme of FD-BSE-based joint suppression of noise and late reverberation to improve the speech recognition accuracy for spoken-dialogue system. First, we optimize the parameter of conventional FD-BSE-based method using the assessment of musical noise measured by higher-order statistics and acoustic model likelihood. Next, to maintain the optimum performance of the system, we proposed the switching scheme using the distance information provided by image sensor. The experimental results show that the proposed approach improves the word recognition accuracy.

Keywords

blind source separation; frequency-domain analysis; image sensors; interactive systems; optimisation; reverberation; signal denoising; speech recognition; FD-BSE-based joint noise suppression; acoustic model likelihood; automatic optimization scheme; dereverberation; distance information; frequency-domain blind signal extraction; higher-order statistics; image sensor; late reverberation; musical noise assessment; semiblind algorithm; speech recognition accuracy; spoken-dialogue system; switching scheme; word recognition accuracy; Accuracy; Joints; Noise; Optimization; Reverberation; Speech; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2013 Asia-Pacific

Conference_Location

Kaohsiung

Type

conf

DOI

10.1109/APSIPA.2013.6694161

Filename

6694161