|
KMID : 0917520010080030123
|
|
Journal of Speech Sciences
2001 Volume.8 No. 3 p.123 ~ p.132
|
|
|
Subword-based Lip Reading Using State-tied HMM
|
|
|
|
|
Abstract
|
|
|
|
In recent years research on HCI technology has been very active and speech recog-nition is being used as its typical method. Its recognition, however is deteriornated with the increase of surrounding noise. To solve this problem, studies concerning the multimodal HCI are being briskly made. This paper describes automated lipreading for bimodal speech recognition on the basis of image- and speech information. It employs audio-visual DB containing 1,074 words from 70 voice and tri-viseme as a recognition unit, and state tied HMM as a recognition model. Performance of automated recognition of 22 to 1,000 words are evaluated to achieve word recognition of 60.5% in terms of 22-word recognizer.
|
|
|
KEYWORD
|
|
|
|
|
|
FullTexts / Linksout information
|
|
|
|
|
|
Listed journal information
|
|
|
|