Can I read DiffWave: A Versatile Diffusion Model for Audio Synthesis on EtoBox?

DiffWave: A Versatile Diffusion Model for Audio Synthesis by Kong, Zhifeng; Ping, Wei; Huang, Jiaji; Zhao, Kexin; Catanzaro, Bryan is a scholarly article available to read on EtoBox.

What is DiffWave: A Versatile Diffusion Model for Audio Synthesis about?

In this work, we propose DiffWave, a versatile diffusion probabilistic model for conditional and unconditional waveform generation. The model is non-autoregressive, and converts the white noise signal into structured waveform through a Markov chain with a constant number of steps at synthesis. It is efficiently trained by optimizing a variant of variational bound on the data likelihood. DiffWave produces high-fidelity audios in different waveform generation tasks, including neural vocoding conditioned on mel spectrogram, class-conditional generation, and unconditional generation. We demonstrate that DiffWave matches a strong WaveNet vocoder in terms of speech quality (MOS: 4.44 versus 4.43), while synthesizing orders of magnitude faster. In particular, it significantly outperforms autoregressive and GAN-based waveform models in the challenging unconditional generation task in terms of audio quality and sample diversity from various automatic and human evaluations.

Author

Kong, Zhifeng; Ping, Wei; Huang, Jiaji; Zhao, Kexin; Catanzaro, Bryan

Published

2020

Language

EN