Speech enhancement by map spectral amplitude estimation using a super-Gaussian speech model

DOI10.1155/ASP.2005.1110MaRDI QIDQ2570552zbMATH OpenWikidataFDO

Authors Thomas Lotter, Peter Vary

Publication date 28 October 2005

Published in EURASIP Journal on Applied Signal Processing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1155/ASP.2005.1110

zbMATH Keywords

MAP estimationspeech enhancementspeech model

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10)

Review text

Summary: This contribution presents two spectral amplitude estimators for acoustical background noise suppression based on maximum a posteriori estimation and super-Gaussian statistical modelling of the speech DFT amplitudes. The probability density function of the speech spectral amplitude is modelled with a simple parametric function, which allows a high approximation accuracy for Laplace- or Gamma-distributed real and imaginary parts of the speech DFT coefficients. Also, the statistical model can be adapted to optimally fit the distribution of the speech spectral amplitudes for a specific noise reduction system. Based on the super-Gaussian statistical model, computationally efficient maximum a posteriori speech estimators are derived, which outperform the commonly applied Ephraim-Malah algorithm.

Recommendations

• Speech spectral modeling and enhancement based on autoregressive conditional heteroscedasticity models
• Multichannel direction-independent speech enhancement using spectral amplitude estimation
• Improved noise suppression filter using self-adaptive estimator of probability of speech absence.
• Multiple statistical models for soft decision in noisy speech enhancement
• Speech and noise power estimation using <scp>G</scp>amma modeling

Cited in

(10)

• Speech spectral modeling and enhancement based on autoregressive conditional heteroscedasticity models
• Multichannel direction-independent speech enhancement using spectral amplitude estimation
• Efficient alternatives to the Ephraim and Malah suppression rule for audio signal enhancement
• The shifted inverse-gamma model for noise-floor estimation in archived audio recordings
• Improved noise suppression filter using self-adaptive estimator of probability of speech absence.
• Speech enhancement with noise estimation and filtration using deep learning models
• Beta-order minimum mean-square error multichannel spectral amplitude estimation for speech enhancement
• Statistically optimal joint multimicrophone MAP estimators under super-Gaussian assumption
• Multiple statistical models for soft decision in noisy speech enhancement
• Low complexity DFT-domain noise PSD tracking using high-resolution periodograms

This page was built for publication: Speech enhancement by map spectral amplitude estimation using a super-Gaussian speech model

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2570552)