Speech recognition system based on mono-camera image

Title
Speech recognition system based on mono-camera image
Authors
고혜승한성민이희창추준욱최재봉최귀원황도식윤인찬
Keywords
Image processing; Lip detection; speech recognition
Issue Date
2012-05
Publisher
대한의용생체공학회 춘계학술대회
Abstract
This paper presents a high-quality speech recognition system with mono-vision camera utilizing template matching and pseudo-hue color space. Lip area is found based on eyes and nose feature point. To grasp subject's intention, system compares vowel template images with lip area images. The template whose contour best matches with the acquired lip feature points is chosen. The result shows that our proposed system provides high accuracy especially in estimating the essential five vowels. While expanding the application to phonemes, it can be applied to help speech-impaired patients to translate their intentions.
URI
http://pubs.kist.re.kr/handle/201004/42656
Appears in Collections:
KIST Publication > Conference Paper
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE