Robust speech recognition using perceptual wavelet denoising and Mel-frequency product spectrum cepstral coefficient features

MaRDI QIDQ3607702zbMATH OpenFDO

Authors Mohamed Cherif Amara Korba, Djemil Messadeg, Rafik Djemili, Hocine Bourouba

Publication date 26 February 2009

zbMATH Keywords

noise robust speech parametrizationpenalized thresholdperceptual wavelet-packet transform

Mathematics Subject Classification ID

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

Recommendations

• A comprehensive noise robust speech parameterization algorithm using wavelet packet decomposition-based denoising and speech feature representation techniques
• Combining speech enhancement and auditory feature extraction for robust speech recognition
• A noise robust feature extraction algorithm using joint wavelet packet subband decomposition and AR modeling of speech signals
• Robust speech recognition using a harmonic model
• Robust Speech Feature Extraction Based on Dynamic Minimum Subband Spectral Subtraction

Cited in

(4)

• Combining speech enhancement and auditory feature extraction for robust speech recognition
• A noise robust feature extraction algorithm using joint wavelet packet subband decomposition and AR modeling of speech signals
• scientific article; zbMATH DE number 2033177 (Why is no real title available?)
• A comprehensive noise robust speech parameterization algorithm using wavelet packet decomposition-based denoising and speech feature representation techniques

This page was built for publication: Robust speech recognition using perceptual wavelet denoising and Mel-frequency product spectrum cepstral coefficient features

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3607702)