Get started
Work

Visual Contribution to Speech Perception: Measuring the Intelligibility of Animated Talking Heads

Year: 2006
Type: article
Abstract: Animated agents are becoming increasingly frequent in research and applications in speech science. An important challenge is to evaluate the effectiveness of the agent in terms of the intelligibility of its visible speech. Sumby and Pollack (1954) proposed a metric to describe the benefit provided by the face relative to the auditory speech presented alone. We extend this metric to allow the comparison of an agent relative to a standard or reference, and also propose a new metric based on the fuzzy logical model of perception (FLMP) to describe the benefit provided by a synthetic animated face relative to the benefit provided by a natural face. The validity of these metrics is tested in three new experiments in which auditory speech is presented at 5 different noise levels and is paired with a) our synthetic talker Baldi versus a natural talker (Bernstein & Eberhardt laser videodisc, 1986) (the reference), b) Baldi’s lips only versus full face, and c) a natural talker lips only versus full face. A valid metric would allow direct comparisons across different experiments and would give measures of the benefit of a synthetic animated face relative to a natural face (or indeed any two conditions) and how this benefit varies as a function of the type of synthetic face, the test items (e.g., syllables versus sentences), different individuals, and applications. In press. Speech and Audio Processing 1
DOI: 10.1155/2007/47891
Language: English
Open Access status: gold
Estimated APC paid: $1,890
OpenAlex ID: W2139055331
FWCI: 3.684
Cites: 35
Cited by: 43
Related to: 10