Improved single channel phase‐aware speech enhancement technique for low signal‐to‐noise ratio signal. Issue 6 (1st August 2016)

• Record Type: Journal Article
• Authors: Samui, Suman; Chakrabarti, Indrajit; Ghosh, Soumya Kanti
• Is Part Of: IET signal processing. Volume 10:Issue 6(2016)
• Page Start: 641
• Page End: 650
• Publication Date: 2016-08-01
• Subjects: speech enhancement -- signal denoising -- spectral analysis -- signal reconstruction -- speech intelligibility -- amplitude estimation; improved single channel phase‐aware speech enhancement technique -- low‐signal‐to‐noise ratio signal -- short‐time spectral amplitude -- phase corruption -- additive noise contamination -- phase‐aware multiband spectral subtraction technique -- spectral amplitude estimates -- noise signal components -- clean speech signal -- signal reconstruction -- composite quality measures -- intelligibility assessment metrics -- objective measure quality evaluation technique; Signal processing -- Periodicals; 621.3822
• DOI: 10.1049/iet-spr.2015.0182
• Languages: English
• ISSNs: 1751-9675

Abstract

Abstract : In the state‐of‐the‐art single channel speech enhancement techniques, the short‐time spectral amplitude is modified while the effect of the phase corruption due to the contamination of additive noise is neglected. This study introduces an improved speech enhancement algorithm based on a phase‐aware multi‐band spectral subtraction technique which estimates the spectral amplitude of the clean speech signal by considering the phase of the speech and noise signal components, and uses the estimated phase of the clean speech signal for signal reconstruction in the time domain. Experimental results show that the proposed algorithm yields better performance in terms of various objective and composite quality measures and other intelligibility assessment metrics while compared with other existing spectral subtraction methods. Using the composite objective measure quality evaluation technique, it is observed that the overall signal quality of the enhanced speech signal is improved on an average by 70% at 0 dB global input signal‐to‐noise ratio by using the proposed approach.