Weakly supervised keyword learning using sparse representations of speech

When applied to speech, Non-negative Matrix Factorization is capable of learning a small vocabulary of words, foregoing any prior linguistic knowledge. This makes it adequate for small-scale speech applications where flexibility is of the utmost importance, e.g. assistive technology for the speech i...

Full description

Saved in:
Bibliographic Details
Main Authors: Driesen, J., Gemmeke, J., Van hamme, H.
Format: Conference Proceeding
Language:English
Subjects:
Acoustics
Adaptation models
Exemplars
Histograms
Lasso
Nonnegative Matrix Factorization
Sparseness
Speech
Speech recognition
Vectors
Vocabulary
Vocabulary Acquisition
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:When applied to speech, Non-negative Matrix Factorization is capable of learning a small vocabulary of words, foregoing any prior linguistic knowledge. This makes it adequate for small-scale speech applications where flexibility is of the utmost importance, e.g. assistive technology for the speech impaired. However, its performance depends on the way its inputs are represented. We propose the use of exemplar-based sparse representations of speech, and explore the influence of some of these representation's basic parameters, such as the total number of exemplars considered and the sparseness imposed on them. We show that the resulting learning performance compares favorably with those of previously proposed approaches.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2012.6287950