BriefGPT.xyz
Feb, 2019
应用于音频合成中的时频特征对抗生成
Adversarial Generation of Time-Frequency Features with application in audio synthesis
HTML
PDF
Andrés Marafioti, Nicki Holighaus, Nathanaël Perraudin, Piotr Majdak
TL;DR
本文研究TF表示的生成建模以及音频的生成，使用短时傅里叶变换讨论了在生成可逆的TF特征上合成音频的挑战和方法，并通过训练GAN演示了基于生成TF建模的潜力。
Abstract
Time-frequency (TF) representations provide powerful and intuitive features for the analysis of time series such as audio. But still,
generative modeling
of audio in the TF domain is a subtle matter. Consequently,
neura
→