Lip-based visual speech recognition system

Aufaclav Zatu Kusuma Frisky, Chien Yao Wang, Andri Santoso, Jia Ching Wang

研究成果: 書貢獻/報告類型會議論文篇章同行評審

6 引文 斯高帕斯(Scopus)

摘要

This paper proposes a system to address the problem of visual speech recognition. The proposed system is based on visual lip movement recognition by applying video content analysis technique. Using spatiotemporal features descriptors, we extracted features from video containing visual lip information. A preprocessing step is employed by removing the noise and enhancing the contrast of images in every frames of video. Extracted feature are used to build a dictionary for kernel sparse representation classifier (K-SRC) in the classification step. We adopted non-negative matrix factorization (NMF) method to reduce the dimensionality of the extracted features. We evaluated the performance of our system using AVLetters and AVLetters2 dataset. To evaluate the performance of our system, we used the same configuration as another previous works. Using AVLetters dataset, the promising accuracies of 67.13%, 45.37%, and 63.12% can be achieved in semi speaker dependent, speaker independent, and speaker dependent, respectively. Using AVLetters2 dataset, our method can achieve accuracy rate of 89.02% for speaker dependent case and 25.9% for speaker independent. This result showed that our proposed method outperforms another methods using same configuration.

原文???core.languages.en_GB???
主出版物標題ICCST 2015 - The 49th Annual IEEE International Carnahan Conference on Security Technology
發行者Institute of Electrical and Electronics Engineers Inc.
頁面315-319
頁數5
ISBN(電子)9781479986910
DOIs
出版狀態已出版 - 21 1月 2016
事件49th Annual IEEE International Carnahan Conference on Security Technology, ICCST 2015 - Taipei, Taiwan
持續時間: 21 9月 201524 9月 2015

出版系列

名字Proceedings - International Carnahan Conference on Security Technology
2015-January
ISSN(列印)1071-6572

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???49th Annual IEEE International Carnahan Conference on Security Technology, ICCST 2015
國家/地區Taiwan
城市Taipei
期間21/09/1524/09/15

指紋

深入研究「Lip-based visual speech recognition system」主題。共同形成了獨特的指紋。

引用此