2002
DOI: 10.1007/3-540-46014-4_32
|View full text |Cite
|
Sign up to set email alerts
|

A Temporal Network of Support Vector Machine Classifiers for the Recognition of Visual Speech

Abstract: Abstract. Speech recognition based on visual information is an emerging research field. We propose here a new system for the recognition of visual speech based on support vector machines which proved to be powerful classifiers in other visual tasks. We use support vector machines to recognize the mouth shape corresponding to different phones produced. To model the temporal character of the speech we employ the Viterbi decoding in a network of support vector machines. The recognition rate obtained is higher tha… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2006
2006
2018
2018

Publication Types

Select...
3
1

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(3 citation statements)
references
References 11 publications
0
3
0
Order By: Relevance
“…its application to streaming connectivity patterns). While such an implementation of SVMs seems rather unusual in EEG-related research, it has already been successfully employed for continuous speech recognition (for instance [ 63 , 64 ]).…”
Section: Discussionmentioning
confidence: 99%
“…its application to streaming connectivity patterns). While such an implementation of SVMs seems rather unusual in EEG-related research, it has already been successfully employed for continuous speech recognition (for instance [ 63 , 64 ]).…”
Section: Discussionmentioning
confidence: 99%
“…Hidden Markov Models (HMM) have been widely used to capture sequentiality of the data by uncovering the underlying event structures [7]. The decision making level techniques include smoothing filters such as moving average or median filters, or more sophisticated Viterbi temporal decoding [8] which incorporates the contextual information before making the final decision.…”
Section: Introductionmentioning
confidence: 99%
“…its application to streaming connectivity patterns). While such an implementation of SVMs seems rather unusual in EEG-related research, it has already been successfully employed for continuous speech recognition (for instance [171], [172]).…”
Section: Summary and Outlook 10 Discussionmentioning
confidence: 99%