Title :
Robust speaker turn role labeling of TV Broadcast News shows
Author :
Damnati, Géraldine ; Charlet, Delphine
Author_Institution :
Orange Labs., France Telecom, Lannion, France
Abstract :
Speaker role recognition in TV Broadcast News shows is addressed in this paper with a particular focus on speaker turn role labeling. A mixed approach combining speaker clustering and analysis of Automatic Speech Recognition output is proposed for assigning speaker turns a role among: anchor, reporter and other. 86% classification accuracy is obtained for automatically segmented speaker turns on a 6.5 hours test corpus of 14 TVBN shows mixing news and conversational speech.
Keywords :
speaker recognition; speech recognition; television broadcasting; TV broadcast news shows; automatic speech recognition; robust speaker turn role labeling; speaker clustering; time 6.5 hr; Accuracy; Feature extraction; Labeling; Speech; Speech processing; Speech recognition; Training; Broadcast News and Conversation speaker distillation; Speaker role; spoken language understanding;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on
Conference_Location :
Prague
Print_ISBN :
978-1-4577-0538-0
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2011.5947650
