University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Effective visually-derived Wiener filtering for audio-visual speech processing

Almajai, I and Milner, B Effective visually-derived Wiener filtering for audio-visual speech processing In: International Conference on Auditory-Visual Speech Processing, 2009-09-10 - ?.

Full text not available from this repository.


This work presents a novel approach to speech enhancement by exploiting the bimodality of speech and the correlation that exists between audio and visual speech features. For speech enhancement, a visually-derived Wiener filter is developed. This obtains clean speech statistics from visual features by modelling their joint density and making a maximum a posteriori estimate of clean audio from visual speech features. Noise statistics for the Wiener filter utilise an audio-visual voice activity detector which classifies input audio as speech or nonspeech, enabling a noise model to be updated. Analysis shows estimation of speech and noise statistics to be effective with speech quality assessed objectively and subjectively measuring the effectiveness of the resulting Wiener filter. The use of this enhancement method is also considered for ASR purposes.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Divisions : Surrey research (other units)
Authors :
Milner, B
Depositing User : Symplectic Elements
Date Deposited : 17 May 2017 11:56
Last Modified : 23 Jan 2020 17:25

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800