Skip to main navigation Skip to search Skip to main content

Speaker dependent visual speech recognition using extended curvature gabor filters

  • Korea Advanced Institute of Science and Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Performance of a speech recognition system often degrades severely under low SNR environment. To overcome this difficulty, the visual signal is also considered as an additional aid these days. In this paper, we address speaker dependent visual speech recognition problem using Extended Curvature Gabor (ECG) wavelet. First, lip image sequences are filtered using the ECG, because the variation of the filter response well represents the lip movement. Next, the distance between the output and training data is calculated using the Multi Dimensional Dynamic Time Warping (MDDTW) with new cost matrix. Finally, the lip sequences are classified into the corresponding utterance. In this process, the parameters of ECG must be selected appropriately, where we compare a simple greedy selection method and selection scheme based on AdaBoost.

Original languageEnglish
Title of host publication2013 IEEE International Conference on Consumer Electronics, ICCE 2013
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages314-315
Number of pages2
ISBN (Print)9781467313612
DOIs
StatePublished - 2013
Event2013 IEEE International Conference on Consumer Electronics, ICCE 2013 - Las Vegas, NV, United States
Duration: 11 Jan 201314 Jan 2013

Publication series

NameDigest of Technical Papers - IEEE International Conference on Consumer Electronics
ISSN (Print)0747-668X

Conference

Conference2013 IEEE International Conference on Consumer Electronics, ICCE 2013
Country/TerritoryUnited States
CityLas Vegas, NV
Period11/01/1314/01/13

Fingerprint

Dive into the research topics of 'Speaker dependent visual speech recognition using extended curvature gabor filters'. Together they form a unique fingerprint.

Cite this