Accurate transcription of broadcast news speech using multiple noisy transcribers and unsupervised reliability metrics.
Kartik AudhkhasiPanayiotis G. GeorgiouShrikanth S. NarayananPublished in: ICASSP (2011)
Keyphrases
- broadcast news
- automatic speech recognition
- story segmentation
- speech recognizer
- speaker identification
- conversational speech
- spoken term detection
- spoken document retrieval
- video retrieval
- speech recognition
- spoken documents
- language processing
- speaker diarization
- video search
- noisy environments
- out of vocabulary
- news video
- automatically generated
- low level features
- word error rate
- speech recognition systems
- hidden markov models
- pattern recognition