DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Daehyun | ko |
dc.contributor.author | Lee, Jongmin | ko |
dc.contributor.author | Kim, Kee-Eung | ko |
dc.date.accessioned | 2016-12-01T01:31:20Z | - |
dc.date.available | 2016-12-01T01:31:20Z | - |
dc.date.created | 2016-11-18 | - |
dc.date.created | 2016-11-18 | - |
dc.date.created | 2016-11-18 | - |
dc.date.issued | 2016-11-20 | - |
dc.identifier.citation | 13th Asian Conference on Computer Vision (ACCV), pp.290 - 302 | - |
dc.identifier.uri | http://hdl.handle.net/10203/214327 | - |
dc.description.abstract | It is well known that automatic lip-reading (ALR), also known as visual speech recognition (VSR), enhances the performance of speech recognition in a noisy environment and also has applications itself. However, ALR is a challenging task due to various lip shapes and ambiguity of visemes (the basic unit of visual speech information). In this paper, we tackle ALR as a classification task using end-to-end neural network based on convolutional neural network and long short-term memory architecture. We conduct single, cross, and multi-view experiments in speaker independent setting with various network configuration to integrate the multi-view data. We achieve 77.9%, 83.8%, and 78.6% classification accuracies in average on single, cross, and multi-view respectively. This result is better than the best score (76%) of preliminary single-view results given by ACCV 2016 workshop on multi-view lip-reading/audiovisual challenges. It also shows that additional view information helps to improve the performance of ALR with neural network architecture. | - |
dc.language | English | - |
dc.publisher | Asian Federation of Computer Vision (AFCV) | - |
dc.title | Multi-View Automatic Lip-Reading using Neural Network | - |
dc.type | Conference | - |
dc.identifier.wosid | 000426193700022 | - |
dc.identifier.scopusid | 2-s2.0-85016123789 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 290 | - |
dc.citation.endingpage | 302 | - |
dc.citation.publicationname | 13th Asian Conference on Computer Vision (ACCV) | - |
dc.identifier.conferencecountry | CH | - |
dc.identifier.conferencelocation | Taipei International Convention Center | - |
dc.identifier.doi | 10.1007/978-3-319-54427-4_22 | - |
dc.contributor.localauthor | Kim, Kee-Eung | - |
dc.contributor.nonIdAuthor | Lee, Daehyun | - |
dc.contributor.nonIdAuthor | Lee, Jongmin | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.