Spectral domain texture analysis for speech enhancement

DOI10.1016/S0031-3203(01)00195-9MaRDI QIDQ1860174zbMATH OpenFDO

Authors Enzo Mumolo

Publication date 20 February 2003

Published in Pattern Recognition (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/S0031-3203(01)00195-9

zbMATH Keywords

heuristic rulesHMM speech recognitionimage relaxationmicro-interruptionsspeech enhancementtexture analysis

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10) Computing methodologies and applications (68U99)

Recommendations

• Comparison of a discrete wavelet transformation and a nonuniform polyphase filterbank applied to spectral-subtraction speech enhancement
• Spectral-subtraction speech enhancement in multirate systems with and without non-uniform and adaptive bandwidths
• Spectral subtraction for speech recognition with increased spectral resolution
• The spectral envelope and its applications.
• Speech enhancement with natural sounding residual noise based on connected time-frequency speech presence regions

Cites work

• All-pole modeling of degraded speech
• Scene Labeling by Relaxation Operations

Cited in

(1)

• scientific article; zbMATH DE number 1952716 (Why is no real title available?)

This page was built for publication: Spectral domain texture analysis for speech enhancement

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1860174)