Author ORCID Identifier

https://orcid.org/ 0000-0002-2916-0134

Document Type

Article

Rights

Available under a Creative Commons Attribution Non-Commercial Share Alike 4.0 International Licence

Disciplines

Computer Sciences

Publication Details

Proceedings of the 2021 IEEE International Symposium on Multimedia IEEE Xplore

Abstract

The synthesis of sound via deep learning methods has recently received much attention. Some problems for deep learning approaches to sound synthesis relate to the amount of data needed to specify an audio signal and the necessity of preserving both the long and short time coherence of the synthesised signal. Visual time-frequency representations such as the log-mel-spectrogram have gained in popularity. The log- mel-spectrogram is a perceptually informed representation of audio that greatly compresses the amount of information required for the description of the sound. However, because of this compression, this representation is not directly invertible. Both signal processing and machine learning techniques have previ- ously been applied to the inversion of the log-mel-spectrogram but they both caused audible distortions in the synthesised sounds due to issues of temporal and spectral coherence. In this paper, we outline the application of a sinusoidal model to the ‘inversion’ of the log-mel-spectrogram for pitched musical instrument sounds outperforming state-of-the-art deep learning methods. The approach could be later used as a general decoding step from spectral to time intervals in neural applications.

DOI

https://doi.org/10.21427/r27x-f169

Funder

SFI

Download


Included in

Engineering Commons

Share

COinS