On the Applicability of Speaker Diarization to Audio Indexing of Non-Speech and Mixed Non-Speech/Speech Video Soundtracks.
Robert MertensPo-Sen HuangLuke R. GottliebGerald FriedlandAjay DivakaranMark Hasegawa-JohnsonPublished in: Int. J. Multim. Data Eng. Manag. (2012)
Keyphrases
- audio stream
- broadcast news
- speaker diarization
- speech recognition
- speaker identification
- content based video retrieval
- audio visual
- audio signals
- video streams
- speech signal
- automatic speech recognition
- audio features
- video search
- multimedia
- video database
- digital audio
- noisy environments
- content based retrieval
- natural language processing
- video sequences
- emotion recognition
- speaker verification
- multimedia data
- image classification