Conditional Spoken Digit Generation with StyleGAN

This paper adapts a StyleGAN model for speech generation with minimal or no conditioning on text. StyleGAN is a multiscale convolutional GAN capable of hierarchically capturing data structure and latent variation on multiple spatial (or temporal) levels. The model has previously achieved impressive results on facial image generation, and it is appealing to audio applications due to similar multi-level structures present in the data. In this paper, we train a StyleGAN to generate melspectrograms on the Speech Commands dataset, which contains spoken digits uttered by multiple speakers in varying acoustic conditions. In a conditional setting our model is conditioned on the digit identity, while learning the remaining data variation remains an unsupervised task. We compare our model to the current unsupervised state-of-the-art speech synthesis GAN architecture, the WaveGAN, and show that the proposed model outperforms according to numerical measures and subjective evaluation by listening tests.

DOI

10.21437/Interspeech.2020-1461

Citation

Palkama, K, Juvela, L & Ilin, A 2020, Conditional Spoken Digit Generation with StyleGAN. in Proceedings of Interspeech. Interspeech, International Speech Communication Association (ISCA), pp. 3166-3170, Interspeech, Shanghai, China, 25/10/2020. https://doi.org/10.21437/Interspeech.2020-1461

Permanent link to this item

https://urn.fi/URN:NBN:fi:aalto-202101251433

Collections

[article-cris] Perustieteiden korkeakoulu / SCI

Show all metadata

Conditional Spoken Digit Generation with StyleGAN

Access rights

URL

Journal Title

Journal ISSN

Volume Title

Authors

Date

Department

Major/Subject

Mcode

Degree programme

Language

Pages

Series

Abstract

Description

Keywords

Other note

DOI

Citation

Permanent link to this item

Collections