A Bag-of-Audio-Words Approach for Snore Sounds' Excitation Localisation.
Maximilian SchmittChristoph JanottVedhas PanditKun QianClemens HeiserWerner HemmertBjörn W. SchullerPublished in: ITG Symposium on Speech Communication (2016)
Keyphrases
- automatic transcription
- environmental sounds
- audio content
- acoustic features
- audio signal
- bag of words
- n gram
- multimedia
- visual features
- human language
- signal processing
- visual information
- text documents
- music information retrieval
- visual speech
- word sense disambiguation
- audio visual
- keywords
- multiword
- multi instance learning
- audio video
- search engine
- natural language processing
- english words
- instance level
- feature set
- related words
- multi instance
- visual data