Paper Info
Title
Audio-Visual Speech Synchronization Detection Using a Bimodal Linear Prediction Model
Abstract
Abstract In this work, we study the problem of detecting audio- visual (AV) synchronization in video segments containing a speaker in frontal head pose. The problem holds important applications in biometrics, for example spoofing detection, and it constitutes an important step in AV segmentation nec- essary for deriving AV fingerprints in multimodal speaker recognition. To attack the problem, we propose a time- evolution model for AV features and derive an analytical approach,to capture the notion of synchronization between them. We report results on an appropriate AV database, us- ing two types of visual features extracted from the speaker’s facial area: geometric ones and features based on the dis- crete cosine image transform. Our results demonstrate that the proposed approach provides substantially better AV syn- chrony detection over a baseline method,that employs mu- tual information, with the geometric visual features outper- forming the image transform ones. Index Terms‐ Audio-Visual Synchronization, Mutual In- formation, Linear Prediction, Visual Features
Year
DOI
Venue
2009
10.1109/CVPRW.2009.5204303
CVPR Workshops
Keywords
Field
DocType
Audio-Visual Synchronization, Mutual Information, Linear Prediction, Visual Features
Fingerprint recognition,Computer science,Image segmentation,Speaker recognition,Artificial intelligence,Computer vision,Facial recognition system,Synchronization,Pattern recognition,Speech recognition,Feature extraction,Mutual information,Biometrics
Conference
Volume
Issue
ISSN
2009
1
2160-7508
ISBN
Citations 
PageRank 
978-1-4244-3994-2
7
0.69
References 
Authors
3
6
Name
Order
Citations
PageRank
Kshitiz Kumar19510.82
Jiri Navratil231431.36
Etienne Marcheret310011.15
Vit Libal4324.32
Ganesh N. Ramaswamy521325.72
Gerasimos Potamianos61113113.80