Phoneme recognition using ICA-based feature extraction and transformation

Authors:
Oh-Wook Kwon;Te-Won Lee
Affiliations:
School of Electrical and Computer Engineering, Chungbuk National University, 48 Gaesin-dong, Heungdeok-gu, Cheongju, Chungbuk 361-763, South Korea;Institute for Neural Computation, University of California, San Diego, 9500 Gilman Drive, La Jolla, CA
Venue:
Signal Processing
Year:
2004

Citing 4
Cited 10

An information-maximization approach to blind separation and blind deconvolution

Neural Computation
Independent component analysis: theory and applications

Independent component analysis: theory and applications
On the Efficient Speech Feature Extraction Based on Independent Component Analysis

Neural Processing Letters
Topographic Independent Component Analysis

Neural Computation

Recognition of human speech phonemes using a novel fuzzy approach

Applied Soft Computing
Continuous speech recognition with sparse coding

Computer Speech and Language
Integrated phoneme subspace method for speech feature extraction

EURASIP Journal on Audio, Speech, and Music Processing
Auditory cortical representations of speech signals for phoneme classification

MICAI'07 Proceedings of the artificial intelligence 6th Mexican international conference on Advances in artificial intelligence
Independent shape component-based human activity recognition via Hidden Markov Model

Applied Intelligence
Evolutionary cepstral coefficients

Applied Soft Computing
Pattern recognition in multivariate time series: dissertation proposal

Proceedings of the 4th workshop on Workshop for Ph.D. students in information & knowledge management
Recognition of greek phonemes using support vector machines

SETN'06 Proceedings of the 4th Helenic conference on Advances in Artificial Intelligence
Design, analysis and experimental evaluation of block based transformation in MFCC computation for speaker recognition

Speech Communication
Noise-robust speech recognition through auditory feature detection and spike sequence decoding

Neural Computation

Quantified Score

Hi-index	0.08

Visualization

Abstract

We investigate the use of independent component analysis (ICA) for speech feature extraction in speech recognition systems. Although initial research suggested that learning basis functions by ICA for encoding the speech signal in an efficient manner improved recognition accuracy, we observe that this may be true for a recognition tasks with little training data. However, when compared in a large training database to standard speech recognition features such as the mel frequency cepstral coefficients (MFCCs), the ICA-adapted basis functions perform poorly. This is mainly due to the resulting phase sensitivity of the learned speech basis functions and their time shift variance property. In contrast to image processing, phase information is not essential for 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 via the Hilbert transform. 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 performance of the new feature is evaluated for phoneme recognition using the TIMIT speech database and compared with the standard MFCC feature. The phoneme recognition results show promising accuracy, which is comparable to the well-optimized MFCC features.