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, 2019 Import into BibTeX
Subject: Machine Learning: Part 2
Permalink: https://www.aes.org/e-lib/browse.cfm?elib=20303

Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!

This paper costs $33 for non-members and is free for AES members and E-Library subscribers.

Learn more about the AES E-Library

E-Library Location:   /conv/146/10170.pdf

Start a discussion about this paper!