BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shibuya, Takashi, Takida, Yuhta, Mitsufuji, Yuki
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916173914832896
author Shibuya, Takashi
Takida, Yuhta
Mitsufuji, Yuki
author_facet Shibuya, Takashi
Takida, Yuhta
Mitsufuji, Yuki
contents Generative adversarial network (GAN)-based vocoders have been intensively studied because they can synthesize high-fidelity audio waveforms faster than real-time. However, it has been reported that most GANs fail to obtain the optimal projection for discriminating between real and fake data in the feature space. In the literature, it has been demonstrated that slicing adversarial network (SAN), an improved GAN training framework that can find the optimal projection, is effective in the image generation task. In this paper, we investigate the effectiveness of SAN in the vocoding task. For this purpose, we propose a scheme to modify least-squares GAN, which most GAN-based vocoders adopt, so that their loss functions satisfy the requirements of SAN. Through our experiments, we demonstrate that SAN can improve the performance of GAN-based vocoders, including BigVGAN, with small modifications. Our code is available at https://github.com/sony/bigvsan.
format Preprint
id arxiv_https___arxiv_org_abs_2309_02836
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network
Shibuya, Takashi
Takida, Yuhta
Mitsufuji, Yuki
Sound
Machine Learning
Audio and Speech Processing
Generative adversarial network (GAN)-based vocoders have been intensively studied because they can synthesize high-fidelity audio waveforms faster than real-time. However, it has been reported that most GANs fail to obtain the optimal projection for discriminating between real and fake data in the feature space. In the literature, it has been demonstrated that slicing adversarial network (SAN), an improved GAN training framework that can find the optimal projection, is effective in the image generation task. In this paper, we investigate the effectiveness of SAN in the vocoding task. For this purpose, we propose a scheme to modify least-squares GAN, which most GAN-based vocoders adopt, so that their loss functions satisfy the requirements of SAN. Through our experiments, we demonstrate that SAN can improve the performance of GAN-based vocoders, including BigVGAN, with small modifications. Our code is available at https://github.com/sony/bigvsan.
title BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network
topic Sound
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2309.02836