Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Visual voice activity detection with optical flow

Aubrey, Andrew, Hicks, Yulia Alexandrovna ORCID: https://orcid.org/0000-0002-7179-4587 and Chambers, J. 2010. Visual voice activity detection with optical flow. IET Image Processing 4 (6) , pp. 463-472. 10.1049/iet-ipr.2009.0042

Full text not available from this repository.

Abstract

Current voice activity detection methods generally utilise only acoustic information. Therefore they are susceptible to false classification because of the presence of other acoustic sources such as another speaker or non-stationary noise. To address this issue, the authors propose a new method of voice activity detection using solely visual information in the form of a speaker's mouth region. Such video information is not affected by the acoustic environment. Simulations show that a high percentage correct silence detection (CSD) can be obtained with a low percentage false silence detection (FSD). Comparisons with two other visual voice activity detectors show the proposed method to be consistently more accurate, and on average yields a 4% improvement in CSD. The usefulness of the method is confirmed by applying it to a previously published audio–visual convolutive blind source separation algorithm, to increase the intelligibility of a speaker.

Item Type: Article
Date Type: Publication
Status: Published
Schools: Computer Science & Informatics
Engineering
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
T Technology > TA Engineering (General). Civil engineering (General)
Uncontrolled Keywords: audio-visual convolutive blind source separation algorithm; false silence detection; optical flow; acoustic sources; high percentage correct silence detection; visual voice activity detection; video information; acoustic information
Publisher: Institution of Engineering and Technology
ISSN: 1751-9659
Last Modified: 19 Oct 2022 09:45
URI: https://orca.cardiff.ac.uk/id/eprint/22069

Citation Data

Cited 26 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item