Speech modeling and noise removal using a perceptually modified Wiener filter

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Algorithms for spectral subtraction suffer from musical noise effects due to the large gaps in the frequency spectrum created by the subtractive process. Proposed methods to solve this problem used the auditory-masking model in the Wiener filter. Since the auditory-masking threshold (AMT) curve reveals that spectral components above it are perceptible, it can serve as a lower bound in the estimate of the short-term speech spectrum. We propose an improvement of the Wiener filter estimate using perceptual constraints that exploit the auditory masking curve. Using an LPC model, from psychoacoustics we derive an estimate of the spectral density of speech that tends to lower and spread the energy of the musical noise onto other frequencies in the critical band. Objective and subjective evaluations indicate a slightly improved performance over ordinary spectral subtraction and Wiener filtering methods.

Original languageEnglish (US)
Title of host publicationProceedings of the 4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2007
Pages304-308
Number of pages5
StatePublished - Dec 1 2007
Event4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2007 - Innsbruck, Austria
Duration: Feb 14 2007Feb 16 2007

Publication series

NameProceedings of the 4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2007

Other

Other4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2007
CountryAustria
CityInnsbruck
Period2/14/072/16/07

Keywords

  • DSP
  • Speech processing

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Signal Processing

Fingerprint Dive into the research topics of 'Speech modeling and noise removal using a perceptually modified Wiener filter'. Together they form a unique fingerprint.

  • Cite this

    Pinto, R., Spanias, A., & Berisha, V. (2007). Speech modeling and noise removal using a perceptually modified Wiener filter. In Proceedings of the 4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2007 (pp. 304-308). (Proceedings of the 4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2007).