Multi-View Approach for Speaker Turn Role Labeling in TV Broadcast News Shows.
Géraldine DamnatiDelphine CharletPublished in: INTERSPEECH (2011)
Keyphrases
- multi view
- broadcast news
- speaker diarization
- automatic speech recognition
- speaker identification
- single view
- free viewpoint
- multiple views
- depth map
- three dimensional
- d objects
- semi supervised
- speech recognition
- co training
- multi view learning
- active learning
- video retrieval
- video search
- hidden markov models
- natural language