Functional link expansions for nonlinear modeling of audio and speech signals.
Danilo ComminielloSimone ScardapaneMichele ScarpinitiRaffaele ParisiAurelio UnciniPublished in: IJCNN (2015)
Keyphrases
- speech signal
- speaker identification
- multimedia
- automatic speech recognition
- speech recognition
- noisy environments
- signal processing
- automatic speech recognition systems
- acoustic features
- visual information
- image processing
- multiresolution
- multiscale
- adaptive filtering
- broadcast news
- feature extraction
- sound signals
- information retrieval