Segmentation et Regroupement en Locuteurs d'une collection de documents audio (Cross-show speaker diarization) [in French].
Grégor DupuyMickael RouvierSylvain MeignierYannick EstèvePublished in: JEP-TALN-RECITAL 2012 (2012)
Keyphrases
- speaker diarization
- document collections
- audio stream
- bayesian information criterion
- information retrieval
- information retrieval systems
- broadcast news
- image segmentation
- metadata
- multimedia
- speech recognition
- keywords
- text documents
- retrieval systems
- model selection
- multi modal
- test collection
- error rate
- text classification
- edge detection