首页 | 本学科首页   官方微博 | 高级检索  
     


Dual-channel spectral subtraction algorithms based speech enhancement dedicated to a bilateral cochlear implant
Authors:Fathi Kallel  Mondher Frikha  Mohamed Ghorbel  Ahmed Ben Hamida  Christian Berger-Vachon
Affiliation:1. Research Unit in Advances Technologies for Medical and Signals (ATMS), Laboratory of Electronics and Information Technologies (LETI), National Engineering School of Sfax, University of Sfax, Route Soukra km 3, Sfax, B.P.W, 3038, Tunisia;2. PACS Team, INSERM Unit 1028: “Cognition and Brain Dynamics”, Lyon Neurosciences Centre, EPU-ISTIL, Claude Bernard University, Boulevard du 11 Novembre 1918, 69622 Villeurbanne, France
Abstract:In this paper, two speech enhancement algorithms (SEAs) based on spectral subtraction (SS) principle have been evaluated for bilateral cochlear implant (BCI) users. Specifically, dual-channel noise power spectral estimation algorithm using power spectral densities (PSD) and cross power spectral density (CPSD) of the observed signals was studied. The enhanced speech signals were obtained using either Dual Channel Non Linear Spectral Subtraction ‘DC-NLSS’ or Dual-Channel Multi-Band Spectral Subtraction ‘DC-MBSS’ algorithms. For performance evaluation, some objective speech assessment tests relying on Perceptual Evaluation of Speech Quality (PESQ) score and speech Itakura-Saito (IS) distortion measurement were performed to fix the optimal number of frequency band needed in DC-MBSS algorithm. In order to evaluate the speech intelligibility, subjective listening tests were assessed with 50 normal hearing listeners using a specific BCI simulator and with three deafened BCI patients. Experimental results, obtained using French Lafon database corrupted by an additive babble noise at different Signal-to-Noise Ratios (SNR), showed that DC-MBSS algorithm improves speech understanding better than DC-NLSS algorithm for single and multiple interfering noise sources.
Keywords:
本文献已被 ScienceDirect 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号