Phoneme recognition using ICA-based feature extraction and transformation

DOI10.1016/J.SIGPRO.2004.03.004MaRDI QIDQ951564zbMATH OpenOpenAlexFDO

Authors Oh-Wook Kwon, Te-Won Lee

Publication date 27 October 2008

Published in Signal Processing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.sigpro.2004.03.004

zbMATH Keywords

independent component analysisfeature extractionspeech recognition

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10) Natural language processing (68T50)

Recommendations

• A comparative study of several feature transformation and learning methods for phoneme classification
• On the efficient speech feature extraction based on independent component analysis
• scientific article; zbMATH DE number 1708118
• A new speech denoising method based on WPD-ICA feature extraction
• Application of kernel-based feature space transformations and learning methods to phoneme classification

Cited in

(7)

• On the efficient speech feature extraction based on independent component analysis
• A comparative study of several feature transformation and learning methods for phoneme classification
• scientific article; zbMATH DE number 5158970 (Why is no real title available?)
• Noise-robust speech recognition through auditory feature detection and spike sequence decoding
• An independent component analysis algorithm through solving gradient equation combined with kernel density estimation
• scientific article; zbMATH DE number 1708118 (Why is no real title available?)
• Recognition of multiple speech sources using ICA

Describes a project that uses

Uses Software

• FastICA

This page was built for publication: Phoneme recognition using ICA-based feature extraction and transformation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q951564)