Speech enhancement using harmonic regeneration - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2005

Speech enhancement using harmonic regeneration


This paper addresses the problem of single microphone speech enhancement in noisy environments. Common short-time noise reduction techniques introduce harmonic distortion in enhanced speech because of the non reliability of estimators for small signal-to-noise ratios. We propose a new method called Harmonic Regeneration Noise Reduction technique which solves this problem. A fully harmonic signal is calculated based on the distorted signal using a non-linearity to regenerate harmonics in an efficient way. This artificial signal is then used to compute a suppression gain able to preserve the speech harmonics. This method is theoretically analyzed, then objective and formal subjective results are given and show a significant improvement compared to classical noise reduction techniques.
Fichier principal
Vignette du fichier
ICASSP055.pdf (401.58 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00482692 , version 1 (11-05-2010)


  • HAL Id : inria-00482692 , version 1


Cyril Plapous, Claude Marro, Pascal Scalart. Speech enhancement using harmonic regeneration. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'2005), Mar 2005, Philadelphia, United States. ⟨inria-00482692⟩
436 View
997 Download


Gmail Facebook X LinkedIn More