Presentation 2008-10-24
Evaluations of TS-BASE for Speech Enhancement and Binaural Benefits Preservation
Junfeng Li, Shuichi Sakamoto, Satoshi Hongo, Masato Akagi, Yoiti Suzuki,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Hearing aids are expected to help hearing-impaired persons to understand speech especially in noisy environments, which is realized by enhancing the target signal of interest and by the selective binaural hearing processing in human's auditory system. Therefore, an effective system for hearing aids must possess two crucial functions: speech enhancement and binaural benefit preservation. In our previous work, we proposed a two-stage binaural speech enhancement (TS-BASE) approach for hearing aids, in which the interfering signal is estimated by cancelling the target signal through an adaptive filter in the first stage and a time-variant speech enhancer in the second stage. Its effectiveness was confirmed through some simple experiments. To comprehensively evaluate the performance of TS-BASE, in this paper, comprehensive experiments are conducted in various acoustic environments and the evaluations on speech enhancement and binaural cue preservation are performed in terms of objective measures. We report the experimental results along with the general discussions on the TS-BASE performance.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) TS-BASE / Adaptive filter / Wiener filter / Binaural cues / Speech enhancement
Paper # EA2008-79
Date of Issue

Conference Information
Committee EA
Conference Date 2008/10/16(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Engineering Acoustics (EA)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Evaluations of TS-BASE for Speech Enhancement and Binaural Benefits Preservation
Sub Title (in English)
Keyword(1) TS-BASE
Keyword(2) Adaptive filter
Keyword(3) Wiener filter
Keyword(4) Binaural cues
Keyword(5) Speech enhancement
1st Author's Name Junfeng Li
1st Author's Affiliation School of Information Science, Japan Advanced Institute of Science and Technology()
2nd Author's Name Shuichi Sakamoto
2nd Author's Affiliation Research Institute of Electrical Communication, Tohoku University
3rd Author's Name Satoshi Hongo
3rd Author's Affiliation Department of Design and Computer Application, Miyagi National Collage of Technology
4th Author's Name Masato Akagi
4th Author's Affiliation School of Information Science, Japan Advanced Institute of Science and Technology
5th Author's Name Yoiti Suzuki
5th Author's Affiliation Research Institute of Electrical Communication, Tohoku University
Date 2008-10-24
Paper # EA2008-79
Volume (vol) vol.2008
Number (no) 255
Page pp.pp.-
#Pages 6
Date of Issue