Continuous speech recognition based on ICA and geometrical learning

Authors:
Hao Feng;Wenming Cao;Shoujue Wang
Affiliations:
Jiaxing University, China;Institute of Intelligent Information System, Information College, Zhejiang University of Technology, Hangzhou, China;Institute of Semiconductors, Chinese Academy of Science, Beijing, China
Venue:
ICMLC'05 Proceedings of the 4th international conference on Advances in Machine Learning and Cybernetics
Year:
2005

Citing 6
Cited 0

An information-maximization approach to blind separation and blind deconvolution

Neural Computation
On the Efficient Speech Feature Extraction Based on Independent Component Analysis

Neural Processing Letters
The application of DBF neural networks for object recognition

Information Sciences—Informatics and Computer Science: An International Journal
A new development on ANN in China: biomimetic pattern recognition and multi weight vector neurons

RSFDGrC'03 Proceedings of the 9th international conference on Rough sets, fuzzy sets, data mining, and granular computing
Application of multi-weighted neuron for iris recognition

ISNN'05 Proceedings of the Second international conference on Advances in neural networks - Volume Part II
Similarity index for clustering DNA microarray data based on multi-weighted neuron

RSFDGrC'05 Proceedings of the 10th international conference on Rough Sets, Fuzzy Sets, Data Mining, and Granular Computing - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

We investigate the use of independent component analysis (ICA) for speech feature extraction in digits speech recognition systems. We observe that this may be true for recognition tasks based on Geometrical Learning with little training data. In contrast to image processing, phase information is not essential for digits speech recognition. We therefore propose a new scheme that shows how the phase sensitivity can be removed by using an analytical description of the ICA-adapted basis functions. Furthermore, since the basis functions are not shift invariant, we extend the method to include a frequency-based ICA stage that removes redundant time shift information. The digits speech recognition results show promising accuracy. Experiments show that the method based on ICA and Geometrical Learning outperforms HMM in a different number of training samples.