Sparse coding for speech recognition

This paper proposes a novel feature extraction technique for speech recognition based on the principles of sparse coding. The idea is to express a spectro-temporal pattern of speech as a linear combination of an overcomplete set of basis functions such that the weights of the linear combination are...

Full description

Saved in:
Bibliographic Details
Published in2010 IEEE International Conference on Acoustics, Speech and Signal Processing pp. 4346 - 4349
Main Authors Sivaram, G S V S, Nemala, S K, Elhilali, M, Tran, T D, Hermansky, H
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.03.2010
Subjects
Automatic speech recognition
compressive sensing
Dictionaries
Feature extraction
Gabor filters
Image reconstruction
Iterative algorithms
Neurons
sparse coding
Speech recognition
Training data
Vectors
Online AccessGet full text

Cover

More Information
Summary:This paper proposes a novel feature extraction technique for speech recognition based on the principles of sparse coding. The idea is to express a spectro-temporal pattern of speech as a linear combination of an overcomplete set of basis functions such that the weights of the linear combination are sparse. These weights (features) are subsequently used for acoustic modeling. We learn a set of overcomplete basis functions (dictionary) from the training set by adopting a previously proposed algorithm which iteratively minimizes the reconstruction error and maximizes the sparsity of weights. Furthermore, features are derived using the learned basis functions by applying the well established principles of compressive sensing. Phoneme recognition experiments show that the proposed features outperform the conventional features in both clean and noisy conditions.
ISBN:9781424442959
1424442958
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2010.5495649