Title :
Improving acoustic speaker verification with visual Body-Language features
Author :
Bregler, Christoph ; Williams, George ; Rosenthal, Sally ; McDowall, Ian
Author_Institution :
Courant Inst. of Math. Sci., New York Univ., New York, NY
Abstract :
We show how an SVM based acoustic speaker verification system can be significantly improved in incorporating new visual features that capture the speaker´s ldquobody language.rdquo We apply this system to many hours of Internet videos and TV broadcasts of politicians and other public figures. Our data ranges from current and former US election candidates to the Queen of England, the President of France, and the Pope, while giving speeches.
Keywords :
acoustic signal processing; multimedia systems; speaker recognition; support vector machines; video signal processing; Internet video; TV broadcast; acoustic speaker verification; machine vision; multimedia system; support vector machine; visual body-language features; Computer vision; Feature extraction; Histograms; Loudspeakers; Natural languages; Robustness; Speaker recognition; Speech; Support vector machines; Videos; Machine vision; Motion analysis; Multimedia systems; Speaker recognition;
Conference_Titel :
Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on
Conference_Location :
Taipei
Print_ISBN :
978-1-4244-2353-8
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2009.4959982
