Browse > Article

A Study on Spatio-temporal Features for Korean Vowel Lipreading  

오현화 (경북대학교 전자전기컴퓨터학부)
김인철 (경북대학교 전자전기컴퓨터학부)
김동수 (경북대학교 전자전기컴퓨터학부)
진성일 (경북대학교 전자전기컴퓨터학부)
Publication Information
The Journal of the Acoustical Society of Korea / v.21, no.1, 2002 , pp. 19-26 More about this Journal
Abstract
This paper defines the visual basic speech units, visemes and investigates various visual features of a lip for the effective Korean lipreading. First, we analyzed the visual characteristics of the Korean vowels from the database of the lip image sequences obtained from the multi-speakers, thereby giving a definition of seven Korean vowel visemes. Various spatio-temporal features of a lip are extracted from the feature points located on both inner and outer lip contours of image sequences and their classification performances are evaluated by using a hidden Markov model based classifier for effective lipreading. The experimental results for recognizing the Korean visemes have demonstrated that the feature victor containing the information of inner and outer lip contours can be effectively applied to lipreading and also the direction and magnitude of the movement of a lip feature point over time is quite useful for Korean lipreading.
Keywords
Korean lipreading; Korean viseme; Spatio-temporal features;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 /
[ 구현옥 ] / 국어 음운학의 이해
2 Toward Movement-invariant Automatic Lip-reading and Speech Recognition /
[ P. Duchnowski;M. Hunke;D. Busching;U. Meier;A. Waibel ] / IEEE Proc. In. Conf. Acoustics. Speech and Signal Processing
3 입술 파라미터 선정에 따른 바이모달 음성인식 성능 비교 및 검증 /
[ 박병구;김진영;임재열 ] / 한국음향학회지   과학기술학회마을
4 Continuous Optical Automatic Speech Recognition by Lipreading /
[ A. J. Goldschen;O. N. Garcia;E. Petajan ] / Proc. of 28th Asilomar Conf. Signals, System and Computers
5 Automatic Speech Recognition System Using Acoustic and Visual Signals /
[ M. E. Henneke;K.V. Prasad;D. G. Stork ] / Proc. of 29th Asilomar Conf. Signals, Systems and Computers
6 /
[ 김영송 ] / 우리말 소리의 연구
7 Hearing _ips and Seeing Voices /
[ H. McGurk;J. MacDonald ] / Nature   DOI   ScienceOn
8 Visible Speech Modeling and Hybrid Markov Models/Neural Networks Based Learning for Lipreading /
[ A. Rozen;P. Deleglise ] / IEEE In. Joint Symposia on Intelligence and Systems
9 /
[ H. Kaplan;C. J. Bally;C. Garretson ] / Speechreading: A Way to Improve Understanding
10 An Image Transform Approach for HMM Based Automatic Lipreading /
[ G. Potamianos;H. P. Graf;E. Cosatto ] / IEEE In. Conf. Image Processing