Extreme Audio Time Stretching Using Neural Synthesis

Loading...
Thumbnail Image

Access rights

openAccess
acceptedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

2023-06-10

Major/Subject

Mcode

Degree programme

Language

en

Pages

5

Series

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1-5, Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing

Abstract

A deep neural network solution for time-scale modification (TSM) focused on large stretching factors is proposed, targeting environmental sounds. Traditional TSM artifacts such as transient smearing, loss of presence, and phasiness are heavily accentuated and cause poor audio quality when the TSM factor is four or larger. The weakness of established TSM methods, often based on a phase vocoder structure, lies in the poor description and scaling of the transient and noise components, or nuances, of a sound. Our novel solution combines a sines-transients-noise decomposition with an independent WaveNet synthesizer to provide a better description of the noise component and an improve sound quality for large stretching factors. Results of a subjective listening test against four other TSM algorithms are reported, showing the proposed method to be often superior. The proposed method is stereo compatible and has a wide range of applications related to the slow motion of media content.

Description

Keywords

Deep learning, Vocoders, Synthesizers, Neural networks, Signal processing algorithms, Media, Recording

Other note

Citation

Fierro, L, Wright, A, Välimäki, V & Hämäläinen, M 2023, Extreme Audio Time Stretching Using Neural Synthesis . in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) ., 10094738, Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, IEEE, pp. 1-5, IEEE International Conference on Acoustics, Speech, and Signal Processing, Rhodes Island, Greece, 04/06/2023 . https://doi.org/10.1109/ICASSP49357.2023.10094738