Name
Abstract | ||
|---|---|---|
In this paper, we propose an automatic visual speech spotting system adapted for RGB-D cameras and based on Hidden Markov Models (HMMs). Our system is based on two main processing blocks, namely, visual feature extraction and speech spotting and recognition. In feature extraction step, the speaker's face pose is estimated using a 3D face model including a rectangular 3D mouth patch used to precisely extract the mouth region. Then, spatio-temporal features are computed on the extracted mouth region. In the second step, the speech video is segmented by finding the starting and the ending points of meaningful utterances and recognized using Viterbi algorithm. The proposed system is mainly evaluated on an extended version of the MIRACL-VC1 dataset. Experimental results demonstrate that the proposed system can segment and recognize key utterances with a recognition rates of 83 % and a reliability of 81.4 %. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1007/978-3-319-25903-1_49 | ADVANCED CONCEPTS FOR INTELLIGENT VISION SYSTEMS, ACIVS 2015 |
Keywords | Field | DocType |
Human machine interaction,Visual speech spotting,Visual speech features,RGB-camera,Kinect | Computer vision,Mouth region,Pattern recognition,Computer science,Speech recognition,Feature extraction,RGB color model,Artificial intelligence,Hidden Markov model,Spotting,Viterbi algorithm,Human machine interaction | Conference |
Volume | ISSN | Citations |
9386 | 0302-9743 | 3 |
PageRank | References | Authors |
0.50 | 13 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ahmed Rekik | 1 | 29 | 3.11 |
| Achraf Ben-Hamadou | 2 | 57 | 6.47 |
| Walid Mahdi | 3 | 116 | 25.49 |