WaveGrad: Estimating Gradients for Waveform Generation

09/02/2020
by   Nanxin Chen, et al.
5

This paper introduces WaveGrad, a conditional model for waveform generation which estimates gradients of the data density. The model is built on prior work on score matching and diffusion probabilistic models. It starts from a Gaussian white noise signal and iteratively refines the signal via a gradient-based sampler conditioned on the mel-spectrogram. WaveGrad offers a natural way to trade inference speed for sample quality by adjusting the number of refinement steps, and bridges the gap between non-autoregressive and autoregressive models in terms of audio quality. We find that it can generate high fidelity audio samples using as few as six iterations. Experiments reveal WaveGrad to generate high fidelity audio, outperforming adversarial non-autoregressive baselines and matching a strong likelihood-based autoregressive baseline using fewer sequential operations. Audio samples are available at https://wavegrad.github.io/.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/17/2021

WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis

This paper introduces WaveGrad 2, a non-autoregressive generative model ...
research
09/21/2020

DiffWave: A Versatile Diffusion Model for Audio Synthesis

In this work, we propose DiffWave, a versatile Diffusion probabilistic m...
research
02/20/2022

It's Raw! Audio Generation with State-Space Models

Developing architectures suitable for modeling raw audio is a challengin...
research
08/16/2020

Audio Dequantization for High Fidelity Audio Generation in Flow-based Neural Vocoder

In recent works, a flow-based neural vocoder has shown significant impro...
research
03/17/2023

MMFace4D: A Large-Scale Multi-Modal 4D Face Dataset for Audio-Driven 3D Face Animation

Audio-Driven Face Animation is an eagerly anticipated technique for appl...
research
06/07/2021

Learning to Efficiently Sample from Diffusion Probabilistic Models

Denoising Diffusion Probabilistic Models (DDPMs) have emerged as a power...
research
12/03/2019

WaveFlow: A Compact Flow-based Model for Raw Audio

In this work, we present WaveFlow, a small-footprint generative flow for...

Please sign up or login with your details

Forgot password? Click here to reset