Auditory VOCODER: Speech resynthesis from an auditory Mellin representation.
Toshio IrinoRoy D. PattersonHideki KawaharaPublished in: ICASSP (2002)
Keyphrases
- signal processing
- information processing
- evoked potentials
- translation invariant
- cross modal
- visual information
- speech recognition
- pattern recognition
- multi modal
- working memory
- computational model
- object identification
- multiscale
- bayesian networks
- audio visual
- data sets
- image representation
- object recognition
- spoken language