SPEECH RECOGNITION USING HMM BASED ON FUSION OF VISUAL AND AUDITORY INFORMATION

Authors
SHINTANI A OGIHARA A YAMAGUCHI Y HAYASHI Y FUKUNAGA K
Citation
A. Shintani et al., SPEECH RECOGNITION USING HMM BASED ON FUSION OF VISUAL AND AUDITORY INFORMATION, IEICE transactions on fundamentals of electronics, communications and computer science, E77A(11), 1994, pp. 1875-1878
Citations number
NO
Categorie Soggetti
Engineering, Eletrical & Electronic","Computer Science Hardware & Architecture","Computer Science Information Systems
Journal title
IEICE transactions on fundamentals of electronics, communications and computer science → ACNP
ISSN journal
09168508
Volume
E77A
Issue
11
Year of publication
1994
Pages
1875 - 1878
Database
ISI
SICI code
0916-8508(1994)E77A:11<1875:SRUHBO>2.0.ZU;2-I
Abstract
We propose two methods to fuse auditory information and visual informa tion for accurate speech recognition. The first method fuses two kinds of information by using linear combination after calculating two kind s of probabilities by HMM for each word. The second method fuses two k inds of information by using the histogram which expresses the correla tion of them. We have performed experiments comparing the proposed met hods with the conventional method and confirmed the validity of the pr oposed methods.