Automatic metric-based speech segmentation for broadcast news via principal component analysis.
Jeih-Weih HungHsin-Min WangLin-Shan LeePublished in: INTERSPEECH (2000)
Keyphrases
- broadcast news
- story segmentation
- speech transcripts
- principal component analysis
- automatic speech recognition
- speech recognizer
- speaker identification
- spoken document retrieval
- conversational speech
- video search
- spoken documents
- question answering
- spoken term detection
- video retrieval
- speech recognition
- speaker diarization
- image segmentation
- speech segments
- acoustic models
- feature extraction
- news video
- edge detection
- hidden markov models
- out of vocabulary
- noisy environments
- speech signal
- automatically generated
- semi automatic
- feature space
- pattern recognition