DocumentCode :
3529324
Title :
Automatic visual-only language identification: A preliminary study
Author :
Newman, Jacob L. ; Cox, Stephen J.
Author_Institution :
Sch. of Comput. Sci., Univ. of East Anglia, Norwich
fYear :
2009
fDate :
19-24 April 2009
Firstpage :
4345
Lastpage :
4348
Abstract :
We describe experiments in visual-only language identification, in which only lip-shape and lip-motion are used to determine the language of a spoken utterance. We focus on the task of discriminating between two or three languages spoken by the same speaker, and we have recorded a suitable database for these experiments. We use a standard audio language identification approach in which the feature vectors are tokenized and then a language model for each language is estimated over a stream of tokens. Although rate of speaking appeared to affect our results, it was found that different languages spoken at rather similar speeds were as well discriminated as a single language spoken at three extreme speeds, indicating that there is a language effect present in our results.
Keywords :
motion compensation; natural language processing; automatic visual-only language identification; lip-motion; lip-shape; spoken utterance; Active appearance model; Cameras; Computer science; Humans; Jacobian matrices; Natural languages; Spatial databases; Speech processing; Vector quantization; Visual databases; language identification; lip-reading;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on
Conference_Location :
Taipei
ISSN :
1520-6149
Print_ISBN :
978-1-4244-2353-8
Electronic_ISBN :
1520-6149
Type :
conf
DOI :
10.1109/ICASSP.2009.4960591
Filename :
4960591
Link To Document :
بازگشت