Recent developments in automated lip-reading . 2013. Paper doi abstract bibtex Human lip-readers are increasingly being presented as useful in the gathering of forensic evidence but, like all humans, suffer from unreliability. Here we report the results of a long-term study in automatic lip-reading with the objective of converting video-to-text (V2T). The V2T problem is surprising in that some aspects that look tricky, such as real-time tracking of the lips on poor-quality interlaced video from hand-held cameras, but prove to be relatively tractable. Whereas the problem of speaker independent lip-reading is very demanding due to unpredictable variations between people. Here we review the problem of automatic lip-reading for crime fighting and identify the critical parts of the problem.
Downloads: 0
{"_id":"eZe9XbGwm8cZw8fsY","bibbaseid":"anonymous-recentdevelopmentsinautomatedlipreading-2013","bibdata":{"bibtype":"proceeding","type":"proceeding","author":[{"propositions":[],"lastnames":["Bowden"],"firstnames":["Richard"],"suffixes":[]},{"propositions":[],"lastnames":["Cox"],"firstnames":["Stephen"],"suffixes":[]},{"propositions":[],"lastnames":["Harvey"],"firstnames":["Richard"],"suffixes":[]},{"propositions":[],"lastnames":["Lan"],"firstnames":["Yuxuan"],"suffixes":[]},{"propositions":[],"lastnames":["Ong"],"firstnames":["Eng-Jon"],"suffixes":[]},{"propositions":[],"lastnames":["Owen"],"firstnames":["Gari"],"suffixes":[]},{"propositions":[],"lastnames":["Theobald"],"firstnames":["Barry-John"],"suffixes":[]}],"title":"Recent developments in automated lip-reading ","journal":"Proc. SPIE","volume":"8901","number":"","pages":"89010J-89010J-13","abstract":"Human lip-readers are increasingly being presented as useful in the gathering of forensic evidence but, like all humans, suffer from unreliability. Here we report the results of a long-term study in automatic lip-reading with the objective of converting video-to-text (V2T). The V2T problem is surprising in that some aspects that look tricky, such as real-time tracking of the lips on poor-quality interlaced video from hand-held cameras, but prove to be relatively tractable. Whereas the problem of speaker independent lip-reading is very demanding due to unpredictable variations between people. Here we review the problem of automatic lip-reading for crime fighting and identify the critical parts of the problem. ","year":"2013","doi":"10.1117/12.2029464","url":"http://personal.ee.surrey.ac.uk/Personal/R.Bowden/publications/2013/SPIE_2013.pdf","key":"SPIE_2013","id":"SPIE_2013","bibbaseid":"anonymous-recentdevelopmentsinautomatedlipreading-2013","role":"author","urls":{"Paper":"http://personal.ee.surrey.ac.uk/Personal/R.Bowden/publications/2013/SPIE_2013.pdf"},"metadata":{"authorlinks":{}}},"bibtype":"proceeding","biburl":"http://personal.ee.surrey.ac.uk/Personal/R.Bowden/publications/bib_all.bib.html","dataSources":["XrGnDCrhEYgNskWwK"],"keywords":[],"search_terms":["recent","developments","automated","lip","reading"],"title":"Recent developments in automated lip-reading ","year":2013}