Audio-Based Distributional Representations of Meaning Using a Fusion of Feature Encodings.
Giannis KaramanolakisElias IosifAthanasia ZlatintsiAggelos PikrakisAlexandros PotamianosPublished in: INTERSPEECH (2016)
Keyphrases
- multimedia
- multiple features
- feature vectors
- orders of magnitude
- data fusion
- vector representation
- image features
- multimodal fusion
- audio visual
- semantic representations
- visual information
- feature fusion
- multi sensor
- higher level
- co occurrence
- cepstral features
- audio video
- information fusion
- fusion algorithm
- visual data
- relevance feedback
- image registration
- natural language