FAAVSP - The 1st Joint Conference on Facial Analysis, Animation, and
Auditory-Visual Speech Processing

Vienna, Austria
September 11-13, 2015

Speaker-Independent Machine Lip-Reading With Speaker-Dependent Viseme Classifiers

Helen L. Bear, Stephen J. Cox, Richard W. Harvey

University of East Anglia, Norwich, UK

In machine lip-reading, which is identification of speech from visual-only information, there is evidence to show that visual speech is highly dependent upon the speaker [1]. Here, we use a phoneme-clustering method to form new phoneme-to-viseme maps for both individual and multiple speakers. We use these maps to examine how similarly speakers talk visually. We conclude that broadly speaking, speakers have the same repertoire of mouth gestures, where they differ is in the use of the gestures. Index Terms: visual-only speech recognition, computer lipreading, visemes, classification, pattern recognition, speakerindependence

Full Paper

Bibliographic reference.  Bear, Helen L. / Cox, Stephen J. / Harvey, Richard W. (2015): "Speaker-independent machine lip-reading with speaker-dependent viseme classifiers", In FAAVSP-2015, 190-195.