Cognitive Components of Speech at Different Time Scales

Ling Feng, Lars Kai Hansen

AbstractWe discuss the cognitive components of speech at different time scales. We investigate cognitive features of speech including phoneme, gender, height, speaker identity. Integration by feature stacking based on short time MFCCs. Our hypothesis is basically ecological: we assume that features that essentially independent in a reasonable ensemble can be efficiently coded using a sparse independent component representation. This means that supervised and unsupervised learning should result in similar representations. We do indeed find that supervised and unsupervised learning of a model based on identical representations have closely corresponding abilities as classifiers.
KeywordsFeature stacking, Unsupervised learning, Supervised learing, Mixture of factor analyzers
TypeConference paper [Abstract]
ConferenceNIPS Workshop: Advances in Acoustic Models
Year2006    Month December
Electronic version(s)[pdf]
BibTeX data [bibtex]
IMM Group(s)Intelligent Signal Processing


Back  ::  IMM Publications