Softening quantization in bag-of-audio-words.
Stephanie PancoastMurat AkbacakPublished in: ICASSP (2014)
Keyphrases
- automatic transcription
- n gram
- multimedia
- bag of words
- human language
- signal processing
- audio video
- single instance
- audio visual
- word sense disambiguation
- quantization error
- related words
- word recognition
- keywords
- audio signals
- audio stream
- visual information
- text documents
- digital video
- low level
- cross modal
- music information retrieval
- speaker identification
- computational complexity
- image representation
- visual features
- image classification
- information retrieval