AUDASCITY: AUdio Denoising by Adaptive Social CosparsITY

Abstract : This work aims at introducing a new algorithm, AUDASCITY, and comparing its performance to the time-frequency block thresholding algorithm for the ill-posed problem of audio denoising. We propose a heuristics which combines time-frequency structure, cosparsity, and an adaptive scheme to denoise audio signals corrupted with white noise. We report that AUDASCITY outperforms state-of-the-art for each numerical comparison. While there is still room for some perceptual improvements, AUDASCITY's usefulness is shown when used as a front-end for a classification task.
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download

https://hal.inria.fr/hal-01540945
Contributor : Clément Gaultier <>
Submitted on : Friday, June 16, 2017 - 5:39:44 PM
Last modification on : Friday, September 13, 2019 - 9:50:02 AM
Long-term archiving on: Wednesday, January 10, 2018 - 12:58:39 PM

File

AudascityEUSIPCO_CR.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01540945, version 1

Citation

Clément Gaultier, Srđan Kitić, Nancy Bertin, Rémi Gribonval. AUDASCITY: AUdio Denoising by Adaptive Social CosparsITY. 25th European Signal Processing Conference (EUSIPCO), Aug 2017, Kos, Greece. ⟨hal-01540945⟩

Share

Metrics

Record views

1761

Files downloads

416