Comparing Audio and Visual Information for Speech Processing

Dean, David B. and Lucey, Patrick J. and Sridharan, Sridha and Wark, Timothy J. (2005) Comparing Audio and Visual Information for Speech Processing. In: Eighth International Symposium on Signal Processing and Its Applications, 28-31 August 2005, Sydney, Australia.

Full text available as:

	PDF - UNSPECIFIED 118Kb
	Other - UNSPECIFIED 918Kb

Abstract

This paper examines the utility of audio-visual speech for the two related tasks of speech and speaker recognition. A study of the confusion that exists between speaker and speech elements was performed to show that principal component analysis (PCA) based visual speech is considerably better for the task of speaker recognition than for speech. Decision fusion speech and speaker recognition engines were also tested under various levels of acoustic degradation to find that the optimal fusion configuration for speaker recognition was substantially different than that for speech. These results highlight the problem of employing similar visual features for both speech and speaker recognition.

ID Code:	5342
Item Type:	Conference Paper
Additional URLs :	http://ieeexplore.ieee.org/xpl/RecentCon...
Keywords :	speech recognition, speaker recognition, fused hidden markov models, audio, visual
Subjects:	Australian and New Zealand Standard Research Classification > INFORMATION AND COMPUTING SCIENCES (080000) > ARTIFICIAL INTELLIGENCE AND IMAGE PROCESSING (080100) > Pattern Recognition and Data Mining (080109) Australian and New Zealand Standard Research Classification > INFORMATION AND COMPUTING SCIENCES (080000) > ARTIFICIAL INTELLIGENCE AND IMAGE PROCESSING (080100) > Natural Language Processing (080107)
Divisions:	QUT Faculties and Divisions > Faculty of Built Environment and Engineering
Copyright Owner :	Copyright 2005 IEEE
Copyright Statement :	Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Deposited On:	24 Oct 2006
Last Modified:	23 Jan 2009 03:41

Export: EndNote | Dublin Core

Repository Staff Only: item control page