Minimum variance deconvolution based-speech enhancement system for a new generation of hearing aids

Author

Gao, Huiqin ; Savic, Michael ; Sorensen, Jeffrey

Author_Institution

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

fYear

1994

fDate

17-18 Mar 1994

Firstpage

71

Lastpage

74

Abstract

Describes a novel method for the enhancement of speech of a particular speaker in a noisy multispeaker environment. Many potential applications of the method are possible including the implementation in a new generation of hearing aids. The system is based on the minimum variance deconvolution (MVD) algorithm. The method was tested using the TIMIT speech database. The utterances of two speakers were first combined to create a multispeaker environment, and then separated using the MVD algorithm. The intelligibility of the separated and enhanced speech was high. Likewise the frequency spectra of the original speech were very similar to the spectra of the separated and enhanced speech for each of the two speakers

Keywords

hearing aids; speech intelligibility; TIMIT speech database; frequency spectra; hearing aid speech enhancement system; intelligibility improvement; minimum variance deconvolution based-speech enhancement system; noisy multispeaker environment; separated enhanced speech; speaker utterances; Acoustic noise; Backscatter; Deconvolution; Equations; Hearing aids; Loudspeakers; Production systems; Signal processing algorithms; Speech enhancement; Working environment noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Bioengineering Conference, 1994., Proceedings of the 1994 20th Annual Northeast

Conference_Location

Springfield, MA

Print_ISBN

0-7803-1930-3

Type

conf

DOI

10.1109/NEBC.1994.305172

Filename

305172