Timezone: »

 
DiffWave: A Versatile Diffusion Model for Audio Synthesis
Zhifeng Kong

Fri Jul 22 12:30 PM -- 01:00 PM (PDT) @

DiffWave is 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. DiffWave produces high-fidelity audios in different waveform generation tasks, including neural vocoding conditioned on mel spectrogram, class-conditional generation, and unconditional generation. 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.

Author Information

Zhifeng Kong (University of California San Diego)

More from the Same Authors