Audio Inpainting of Music by Means of Neural Networks
×
Cite This
Citation & Abstract
A. Marafioti, S. s, N. Holighaus, and P. Majdak, N. Perraudin, L. l, "Audio Inpainting of Music by Means of Neural Networks," Paper 10170, (2019 March.). doi:
A. Marafioti, S. s, N. Holighaus, and P. Majdak, N. Perraudin, L. l, "Audio Inpainting of Music by Means of Neural Networks," Paper 10170, (2019 March.). doi:
Abstract: We studied the ability of deep neural networks (DNNs) to restore missing audio content based on its context, a process usually referred to as audio inpainting. We focused on gaps in the range of tens of milliseconds. The proposed DNN structure was trained on audio signals containing music and musical instruments, separately, with 64-ms long gaps and represented by time-frequency (TF) coefficients. For music, our DNN significantly outperformed the reference method based on linear predictive coding (LPC), demonstrating a generally good usability of the proposed DNN structure for inpainting complex audio signals like music.
@article{marafioti2019audio,
author={marafioti, andré and s and holighaus, nicki and majdak, piotr and perraudin, nathanaë and l},
journal={journal of the audio engineering society},
title={audio inpainting of music by means of neural networks},
year={2019},
volume={},
number={},
pages={},
doi={},
month={march},}
@article{marafioti2019audio,
author={marafioti, andré and s and holighaus, nicki and majdak, piotr and perraudin, nathanaë and l},
journal={journal of the audio engineering society},
title={audio inpainting of music by means of neural networks},
year={2019},
volume={},
number={},
pages={},
doi={},
month={march},
abstract={we studied the ability of deep neural networks (dnns) to restore missing audio content based on its context, a process usually referred to as audio inpainting. we focused on gaps in the range of tens of milliseconds. the proposed dnn structure was trained on audio signals containing music and musical instruments, separately, with 64-ms long gaps and represented by time-frequency (tf) coefficients. for music, our dnn significantly outperformed the reference method based on linear predictive coding (lpc), demonstrating a generally good usability of the proposed dnn structure for inpainting complex audio signals like music.},}
TY - paper
TI - Audio Inpainting of Music by Means of Neural Networks
SP -
EP -
AU - Marafioti, André
AU - s
AU - Holighaus, Nicki
AU - Majdak, Piotr
AU - Perraudin, Nathanaë
AU - l
PY - 2019
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - March 2019
TY - paper
TI - Audio Inpainting of Music by Means of Neural Networks
SP -
EP -
AU - Marafioti, André
AU - s
AU - Holighaus, Nicki
AU - Majdak, Piotr
AU - Perraudin, Nathanaë
AU - l
PY - 2019
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - March 2019
AB - We studied the ability of deep neural networks (DNNs) to restore missing audio content based on its context, a process usually referred to as audio inpainting. We focused on gaps in the range of tens of milliseconds. The proposed DNN structure was trained on audio signals containing music and musical instruments, separately, with 64-ms long gaps and represented by time-frequency (TF) coefficients. For music, our DNN significantly outperformed the reference method based on linear predictive coding (LPC), demonstrating a generally good usability of the proposed DNN structure for inpainting complex audio signals like music.
We studied the ability of deep neural networks (DNNs) to restore missing audio content based on its context, a process usually referred to as audio inpainting. We focused on gaps in the range of tens of milliseconds. The proposed DNN structure was trained on audio signals containing music and musical instruments, separately, with 64-ms long gaps and represented by time-frequency (TF) coefficients. For music, our DNN significantly outperformed the reference method based on linear predictive coding (LPC), demonstrating a generally good usability of the proposed DNN structure for inpainting complex audio signals like music.
Authors:
Marafioti, Andrés; Holighaus, Nicki; Majdak, Piotr; Perraudin, Nathanaël
Affiliations:
Austrian Academy of Sciences, Vienna, Austria; Swiss Data Science Center, Switzerland(See document for exact affiliation information.)
AES Convention:
146 (March 2019)
Paper Number:
10170
Publication Date:
March 10, 2019Import into BibTeX
Subject:
Machine Learning: Part 2
Permalink:
http://www.aes.org/e-lib/browse.cfm?elib=20303