Paper Info
Title
Insights into machine lip reading
Abstract
Computer lip-reading is one of the great signal processing challenges. Not only is the signal noisy, it is variable. However it is almost unknown to compare the performance with human lip-readers. Partly this is because of the paucity of human lip-readers and partly because most automatic systems only handle data that are trivial and therefore not representative of human speech. Here we generate a multiview dataset using connected words that can be analysed by an automatic system, based on linear predictive trackers and active appearance models, and human lip-readers. The automatic system we devise has a viseme accuracy of ≈ 46% which is comparable to poor professional human lip-readers. However, unlike human lip-readers our system is good at guessing its fallibility.
Year
DOI
Venue
2012
10.1109/ICASSP.2012.6288999
ICASSP
Keywords
Field
DocType
speech processing,signal noisy,signal processing,speech recognition,visual speech,active appearance model,automatic system,human speech,machine lip reading,viseme accuracy,linear predictive trackers,professional human lip readers,computer lip reading,automated lip-reading,multiview dataset,hidden markov models,accuracy,visualization,speech
Speech processing,Signal processing,Speech analytics,Pattern recognition,Voice activity detection,Viseme,Computer science,Visualization,Active appearance model,Speech recognition,Artificial intelligence,Hidden Markov model
Conference
ISSN
ISBN
Citations 
1520-6149 E-ISBN : 978-1-4673-0044-5
978-1-4673-0044-5
3
PageRank 
References 
Authors
0.40
0
3
Name
Order
Citations
PageRank
Yuxuan Lan11198.21
R. Harvey2623.98
Barry-John Theobald333225.39