Efficient Adversarial Audio Synthesis VIA Progressive Upsampling

This paper proposes a novel generative model called PUGAN, which progressively synthesizes high-quality audio in a raw waveform. Progressive upsampling GAN (PUGAN) leverages the progressive generation of higher-resolution output by stacking multiple encoder-decoder architectures. Compared to an exis...

Full description

Saved in:
Bibliographic Details
Main Authors: Cho, Youngwoo, Chang, Minwook, Lee, Sanghyeon, Lee, Hyoungwoo, Kim, Gerard Jounghyun, Choo, Jaegul
Format: Conference Proceeding
Language:English
Subjects:
Acoustics
Conferences
Decoding
Generative adversarial networks
generative adversarial networks (GANs)
Real-time sound effect synthesis
Real-time systems
Speech processing
Stacking
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper proposes a novel generative model called PUGAN, which progressively synthesizes high-quality audio in a raw waveform. Progressive upsampling GAN (PUGAN) leverages the progressive generation of higher-resolution output by stacking multiple encoder-decoder architectures. Compared to an existing state-of-the-art model called WaveGAN, which uses a single decoder architecture, our model generates audio signals and converts them to a higher resolution in a progressive manner, while using a significantly smaller number of parameters, e.g., 3.17x smaller for 16 kHz output, than WaveGAN. Our experiments show that the audio signals can be generated in real time with a comparable quality to that of WaveGAN in terms of the inception scores and human perception.
ISSN:2379-190X
DOI:10.1109/ICASSP39728.2021.9413954