Abstract
AbstractThis paper presents a novel approach to speech enhancement that is based on compressed sensing. Voice activity detection is performed to identify the speech and non-speech (pauses) frames. The non-speech frame is then used for noise estimation. Orthogonal matching pursuit is employed to obtain improved speech by sparse recovery. During pauses, the noise is measured and used to update the orthogonal matching pursuit termination threshold. The proposed technique is tested for white noise. The comparison with a few state of art algorithms is carried out in terms of segmental signal-to-noise ratio and perceptual evaluation of speech quality. The outcomes show the benefits of the proposed approach.KeywordsCompressed sensingOrthogonal matching pursuitSpeech enhancementVoice activity detection
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
