Presentation | 2004/12/3 Japanese Lip-Reading System Alaa Sagheer, Naoyuki Tsuruta, Rin-Ichiro Taniguchi, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Lip-reading is one of the most fertile topics of interface with computer, since it can smooth the Human-Computer Interface by introducing Human-Human interaction mechanism. In this talk, we introduce a novel Japanese lip-reading system combines our group's model, Hypercolumn neural network Model (HCM), with Hidden Markov Model (HMM). HCM is used to extract the visual speech features while HMM is used for recognition. The proposed lip-reading system can work under varying lip positions and sizes. Our experiments were carried out using multiple sentences of Japanese language. All images were captured in a natural environment without using a special lighting or lip markers. Experimental results are shown to compare favourably with the results of two reported approaches : Self Organizing Map (SOM) using same database set and Discrete Cosine Transform (DCT) using different database set. HCM provides better performance than both approaches. This demonstrates that HCM can extract and classify features in a better manner than SOM and DCT. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Lip-reading / Visual features extraction / Hypercolumn model / Self organizing map / Hidden markov model |
Paper # | NC2004-113 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 2004/12/3(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Neurocomputing (NC) |
---|---|
Language | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Japanese Lip-Reading System |
Sub Title (in English) | |
Keyword(1) | Lip-reading |
Keyword(2) | Visual features extraction |
Keyword(3) | Hypercolumn model |
Keyword(4) | Self organizing map |
Keyword(5) | Hidden markov model |
1st Author's Name | Alaa Sagheer |
1st Author's Affiliation | Department of Intelligent Systems, Kyushu University() |
2nd Author's Name | Naoyuki Tsuruta |
2nd Author's Affiliation | Department of Electronics Engineering and Computer Science, Fukuoka University |
3rd Author's Name | Rin-Ichiro Taniguchi |
3rd Author's Affiliation | Department of Intelligent Systems, Kyushu University |
Date | 2004/12/3 |
Paper # | NC2004-113 |
Volume (vol) | vol.104 |
Number (no) | 502 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |