Bandwidth extension of musical audio signals with no side information using dilated convolutional neural networks - Archive ouverte HAL Access content directly
Conference Papers Year : 2020

Bandwidth extension of musical audio signals with no side information using dilated convolutional neural networks

Abstract

Bandwidth extension has a long history in audio processing. While speech processing tools do not rely on side information, production-ready bandwidth extension tools of general audio signals rely on side information that has to be transmitted alongside the bitstream of the low frequency part, mostly because polyphonic music has a more complex and less predictable spectral structure than speech. This paper studies the benefit of considering a dilated fully convolutional neural network to perform the bandwidth extension of musical audio signals with no side information on the magnitude spectra. Experimental evaluation using two public datasets, medley-solos-db and gtzan, respectively of monophonic and polyphonic music demonstrate that the proposed architecture achieves state of the art performance.
Fichier principal
Vignette du fichier
lagrangeBandwidthExtension.pdf (178.56 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02473457 , version 1 (10-02-2020)
hal-02473457 , version 2 (18-03-2020)

Identifiers

  • HAL Id : hal-02473457 , version 2

Cite

Mathieu Lagrange, Félix Gontier. Bandwidth extension of musical audio signals with no side information using dilated convolutional neural networks. IEEE ICASSP, May 2020, Barcelona, Spain. ⟨hal-02473457v2⟩
155 View
1217 Download

Share

Gmail Facebook X LinkedIn More