The University of Southampton
University of Southampton Institutional Repository

Compressive speech enhancement

Compressive speech enhancement
Compressive speech enhancement
This paper presents an alternative approach to speech enhancement by using compressed sensing (CS). CS is a new sampling theory, which states that sparse signals can be reconstructed from far fewer measurements than the Nyquist sampling. As such, CS can be exploited to reconstruct only the sparse components (e.g., speech) from the mixture of sparse and non-sparse components (e.g., noise). This is possible because in a time-frequency representation, speech signal is sparse whilst most noise is non-sparse. Derivation shows that on average the signal to noise ratio (SNR) in the compressed domain is greater or equal than the uncompressed domain. Experimental results concur with the derivation and the proposed CS scheme achieves better or similar perceptual evaluation of speech quality (PESQ) scores and segmental SNR compared to other conventional methods in a wide range of input SNR.
compressed sensing, speech enhancement, sparsity
0167-6393
757-768
Low, Siow Yong
8fd903a4-b0b0-4c1c-9cc7-c2fe87109376
Pham, Duc Son
bed8741d-4f75-4252-92d4-52cdb31dca45
Venkatesh, Svetha
fb5e058d-1faf-4dc1-9e32-6af80dc0a00b
Low, Siow Yong
8fd903a4-b0b0-4c1c-9cc7-c2fe87109376
Pham, Duc Son
bed8741d-4f75-4252-92d4-52cdb31dca45
Venkatesh, Svetha
fb5e058d-1faf-4dc1-9e32-6af80dc0a00b

Low, Siow Yong, Pham, Duc Son and Venkatesh, Svetha (2013) Compressive speech enhancement. Speech Communication, 55 (6), 757-768. (doi:10.1016/j.specom.2013.03.003).

Record type: Article

Abstract

This paper presents an alternative approach to speech enhancement by using compressed sensing (CS). CS is a new sampling theory, which states that sparse signals can be reconstructed from far fewer measurements than the Nyquist sampling. As such, CS can be exploited to reconstruct only the sparse components (e.g., speech) from the mixture of sparse and non-sparse components (e.g., noise). This is possible because in a time-frequency representation, speech signal is sparse whilst most noise is non-sparse. Derivation shows that on average the signal to noise ratio (SNR) in the compressed domain is greater or equal than the uncompressed domain. Experimental results concur with the derivation and the proposed CS scheme achieves better or similar perceptual evaluation of speech quality (PESQ) scores and segmental SNR compared to other conventional methods in a wide range of input SNR.

This record has no associated files available for download.

More information

e-pub ahead of print date: 26 March 2013
Published date: July 2013
Keywords: compressed sensing, speech enhancement, sparsity
Organisations: Southampton Wireless Group

Identifiers

Local EPrints ID: 368033
URI: http://eprints.soton.ac.uk/id/eprint/368033
ISSN: 0167-6393
PURE UUID: b2d80dbe-1f8b-4567-8a41-4abf2b30ab80

Catalogue record

Date deposited: 10 Sep 2014 13:48
Last modified: 14 Mar 2024 17:40

Export record

Altmetrics

Contributors

Author: Siow Yong Low
Author: Duc Son Pham
Author: Svetha Venkatesh

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×