Speech Quality Enhancement for In-Ear Microphone Based on Neural Network

Hochong PARK  Yong-Shik SHIN  Seong-Hyeon SHIN  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E102-D   No.8   pp.1594-1597
Publication Date: 2019/08/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2018EDL8249
Type of Manuscript: LETTER
Category: Speech and Hearing
Keyword: 
in-ear microphone,  neural network,  noise-free speech,  speech quality enhancement,  

Full Text: PDF(468.4KB)>>
Buy this Article




Summary: 
Speech captured by an in-ear microphone placed inside an occluded ear has a high signal-to-noise ratio; however, it has different sound characteristics compared to normal speech captured through air conduction. In this study, a method for blind speech quality enhancement is proposed that can convert speech captured by an in-ear microphone to one that resembles normal speech. The proposed method estimates an input-dependent enhancement function by using a neural network in the feature domain and enhances the captured speech via time-domain filtering. Subjective and objective evaluations confirm that the speech enhanced using our proposed method sounds more similar to normal speech than that enhanced using conventional equalizer-based methods.