Binaural speech enhancement using a codebook based approach

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceeding

Abstract

Enhancement of speech in non stationary noise environments has been a major research topic due to its wide range of applications, e.g., in hearing aids. This paper proposes a method for performing dual channel speech enhancement. The proposed method involves the estimation of speech and noise short term predictor (STP) parameters using a codebook based approach, when we have access to binaural noisy signals. The estimated STP parameters are subsequently used for enhancement in a dual channel scenario. Objective measures indicate, that the proposed method is able to improve the speech intelligibility and quality.
Close

Details

Enhancement of speech in non stationary noise environments has been a major research topic due to its wide range of applications, e.g., in hearing aids. This paper proposes a method for performing dual channel speech enhancement. The proposed method involves the estimation of speech and noise short term predictor (STP) parameters using a codebook based approach, when we have access to binaural noisy signals. The estimated STP parameters are subsequently used for enhancement in a dual channel scenario. Objective measures indicate, that the proposed method is able to improve the speech intelligibility and quality.
Original languageEnglish
Title of host publicationAcoustic Signal Enhancement (IWAENC), 2016 IEEE International Workshop on
Number of pages5
PublisherIEEE
Publication dateSep 2016
ISBN (Print)978-1-5090-2007-2
ISBN (Electronic)978-1-5090-2008-9
DOI
StatePublished - Sep 2016
Publication categoryResearch
Peer-reviewedYes
EventInternational Workshop on Acoustic echo and Noise Control (IWAENC) 2016 - Xi'an, China
Duration: 13 Sep 2016 → …

Conference

ConferenceInternational Workshop on Acoustic echo and Noise Control (IWAENC) 2016
LocationXi'an
LandChina
Periode13/09/2016 → …
SeriesProceedings of the International Workshop in Acoustic Echo and Noise Control (IWAENC)
ID: 257609265