Detection, diarization, and transcription of far-field lecture speech.
Jing HuangEtienne MarcheretKarthik VisweswariahVit LibalGerasimos PotamianosPublished in: INTERSPEECH (2007)
Keyphrases
- speaker diarization
- speech activity detection
- detection accuracy
- speech recognition
- detection algorithm
- false alarms
- speaker identification
- object detection
- detection method
- endpoint detection
- speech recognition systems
- detection rate
- automatic detection
- speech signal
- spoken language
- noisy environments
- computer vision
- video recordings
- speech synthesis
- false positives
- speech recognition technology
- user interface
- video sequences