A regressive boosting approach to automatic audio tagging based on soft annotator fusion.
Rémi FoucardSlim EssidMathieu LagrangeGaël RichardPublished in: ICASSP (2012)
Keyphrases
- semi automatic
- manual annotation
- multimedia
- combining multiple
- data fusion
- metadata
- information fusion
- semantic annotation
- speech music discrimination
- multimodal fusion
- ensemble methods
- data sets
- fully automatic
- cost sensitive
- remote sensing
- ensemble learning
- multiresolution
- fusion algorithm
- weak learners
- feature selection
- audio video
- learning algorithm
- neural network