On Phonemes as Cognitive Components of Speech

Ling Feng, Lars Kai Hansen

AbstractCOgnitive Component Analysis (COCA) defined as the process
of unsupervised grouping of data such that the ensuing
group structure is well-aligned with that resulting from human
cognitive activity, has been explored on phoneme data. Statistical
regularities have been revealed at multiple time scales.
The basic features are 25-dimensional short time (20ms) melfrequency
weighted cepstral coefficients. Features are integrated
by means of stacking to obtain features at longer time
scales. Energy based sparsification is carried out to achieve
sparse representations. Our hypothesis is ecological: we assume
that features that essentially independent in a context
defined ensemble can be efficiently coded using a sparse independent
component representation. This means that supervised
and unsupervised learning should result in similar representations.
We indeed find that supervised and unsupervised
learning seem to identify similar representations, here, measured
by the classification similarity.
KeywordsCognitive Component Analysis, Unsupervised Learning, Supervised Learning, Phoneme Classification.
TypeMisc [Presentation]
Year2008    Month June
PublisherDepartment of Informatics and Mathematical Modelling, Technical University of Denmark
AddressRichard Petersens Plads, Building 321, DK-2800 Kgs. Lyngby
NoteSlides from the talk in the 1st IAPR Workshop on Cognitive Information Processing (CIP'08)
Electronic version(s)[pdf]
BibTeX data [bibtex]
IMM Group(s)Intelligent Signal Processing