Model-free anchor speaker turn detection for automatic chapter generation in broadcast news.
Delphine CharletPublished in: ICASSP (2010)
Keyphrases
- model free
- broadcast news
- automatic speech recognition
- speaker diarization
- speaker identification
- reinforcement learning
- speech transcripts
- speech recognition
- function approximation
- story segmentation
- video search
- speech recognizer
- noisy environments
- neural network
- video retrieval
- acoustic models
- spoken document retrieval
- question answering
- hidden markov models
- e learning