Speech enhancement for in‐vehicle voice control systems using wavelet analysis and blind source separation. Issue 4 (14th January 2019)

• Record Type: Journal Article
• Authors: Lei, Peng; Chen, Meiling; Wang, Jun
• Is Part Of: IET intelligent transport systems. Volume 13:Issue 4(2019)
• Page Start: 693
• Page End: 702
• Publication Date: 2019-01-14
• Subjects: automobiles -- blind source separation -- independent component analysis -- Fourier transforms -- signal denoising -- wavelet transforms -- speech enhancement; in‐vehicle voice control systems -- wavelet analysis -- blind source separation -- signal‐to‐interference ratio -- speech‐based intelligent driver assistant systems -- serious impact -- voice control commands -- speech enhancement method -- complicated automobile environment -- typical speech signals -- automatic selection method -- optimal wavelet basis -- signal denoising performance -- mixed signals -- fast‐independent component analysis algorithm -- inverse short‐time Fourier transform -- separated signals; Intelligent transportation systems -- Periodicals; Electronics in transportation -- Periodicals; 388.31205
• DOI: 10.1049/iet-its.2018.5094
• Languages: English
• ISSNs: 1751-956X

Abstract

Abstract : Multiple sources of interference and low signal‐to‐interference ratio are two major challenges to speech‐based intelligent driver assistant systems. They will have a serious impact on the performance of voice control commands. To solve this problem, this study proposes a speech enhancement method based on wavelet analysis and blind source separation in a complicated automobile environment. Firstly, according to the characteristics of typical speech signals, an automatic selection method of optimal wavelet basis is given to optimise the signal denoising performance. Secondly, the mixed signals are separated by a complex fast‐independent component analysis (ICA) algorithm, and then the inverse short‐time Fourier transform is utilised to obtain the separated signals in time domain. Finally, experiments are carried out to demonstrate the effectiveness of the proposed method. Results show that its performance in terms of a correlation coefficient can be improved by about 7% compared with that of the conventional method only using fast‐ICA.