Segmentation of TV shows into scenes using speaker diarization and speech recognition.
Hervé BredinPublished in: ICASSP (2012)
Keyphrases
- speaker diarization
- speech recognition
- tv shows
- topic segmentation
- closed captions
- video clips
- bayesian information criterion
- automatic speech recognition
- language model
- hidden markov models
- speech signal
- speaker identification
- pattern recognition
- image segmentation
- computer vision
- noisy environments
- image classification
- word segmentation
- handwriting recognition
- word error rate
- image sequences