ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper Adversarial Audio Synthesis Using a Harmonic-Percussive Discriminator
Cited 1 time in scopus Download 0 time Share share facebook twitter linkedin kakaostory
Authors
Jihyun Lee, Hyungseob Lim, Chanwoo Lee, Inseon Jang, Hong-Goo Kang
Issue Date
2022-05
Citation
International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2022, pp.961-965
Language
English
Type
Conference Paper
DOI
https://dx.doi.org/10.1109/ICASSP43922.2022.9746826
Project Code
21ZH1200, The research of the fundamental media·contents technologies for hyper-realistic media space, Lee Tae Jin
Abstract
In this paper, we propose a discriminator design scheme for generative adversarial network-based audio signal generation. Unlike conventional discriminators that take an entire signal as input, our discriminator separates the audio signal into harmonic and percussive components and analyzes each component independently. The rationale behind this idea is that conventional discriminators cannot reliably capture subtle distortions in audio signals, which have complicated time-frequency characteristics. By considering the time-frequency resolution of audio signals, our proposed method encourages the generator to better reconstruct harmonic and percussive features, both of which are critical for the quality of the generated signals. Listening tests show that our framework significantly enhances the stability of pitches and generates clearer piano samples compared to a baseline.
KSP Keywords
Audio signal, Audio synthesis, Design Scheme, Signal generation, Time-frequency characteristics, generative adversarial network, listening tests, network-based, time frequency(T-F), time-frequency resolution