Learning static spectral weightings for speech intelligibility enhancement in noise

Tang, Y and Cooke, M 2018, 'Learning static spectral weightings for speech intelligibility enhancement in noise' , Computer Speech & Language, 49 , pp. 1-16.

[img] PDF - Accepted Version
Restricted to Repository staff only until 8 November 2019.

Download (678kB) | Request a copy

Abstract

Near-end speech enhancement works by modifying speech prior to presentation in a noisy environment, typically operating under a constraint of limited or no increase in speech level. One issue is the extent to which near-end enhancement techniques require detailed estimates of the masking environment to function effectively. The current study investigated speech modification strategies based on reallocating energy statically across the spectrum using masker-specific spectral weightings. Weighting patterns were learned offline by maximising a glimpse-based objective intelligibility metric. Keyword scores in sentences in the presence of stationary and fluctuating maskers increased, in some cases by very substantial amounts, following the application of masker- and SNR-specific spectral weighting. A second experiment using generic masker-independent spectral weightings that boosted all frequencies above 1 kHz also led to significant gains in most conditions. These findings indicate that energy-neutral spectral weighting is a highly-effective near-end speech enhancement approach that places minimal demands on detailed masker estimation.

Item Type: Article
Schools: Schools > School of Computing, Science and Engineering > Salford Innovation Research Centre (SIRC)
Journal or Publication Title: Computer Speech & Language
Publisher: Elsevier
ISSN: 0885-2308
Related URLs:
Funders: European Commission
Depositing User: Y Tang
Date Deposited: 18 Dec 2017 08:39
Last Modified: 11 Jan 2018 02:53
URI: http://usir.salford.ac.uk/id/eprint/44654

Actions (login required)

Edit record (repository staff only) Edit record (repository staff only)

Downloads

Downloads per month over past year