DeepAI AI Chat
Log In Sign Up

Diff-TTS: A Denoising Diffusion Model for Text-to-Speech

by   Myeonghun Jeong, et al.

Although neural text-to-speech (TTS) models have attracted a lot of attention and succeeded in generating human-like speech, there is still room for improvements to its naturalness and architectural efficiency. In this work, we propose a novel non-autoregressive TTS model, namely Diff-TTS, which achieves highly natural and efficient speech synthesis. Given the text, Diff-TTS exploits a denoising diffusion framework to transform the noise signal into a mel-spectrogram via diffusion time steps. In order to learn the mel-spectrogram distribution conditioned on the text, we present a likelihood-based optimization method for TTS. Furthermore, to boost up the inference speed, we leverage the accelerated sampling method that allows Diff-TTS to generate raw waveforms much faster without significantly degrading perceptual quality. Through experiments, we verified that Diff-TTS generates 28 times faster than the real-time with a single NVIDIA 2080Ti GPU.


page 1

page 2

page 3

page 4


DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs

Denoising diffusion probabilistic models (DDPMs) are expressive generati...

Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech

Recently, denoising diffusion probabilistic models and generative score ...

TransFusion: Transcribing Speech with Multinomial Diffusion

Diffusion models have shown exceptional scaling properties in the image ...

ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech

Denoising diffusion probabilistic models (DDPMs) have recently achieved ...

HouseDiffusion: Vector Floorplan Generation via a Diffusion Model with Discrete and Continuous Denoising

The paper presents a novel approach for vector-floorplan generation via ...

WaveFlow: A Compact Flow-based Model for Raw Audio

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

FeatherTTS: Robust and Efficient attention based Neural TTS

Attention based neural TTS is elegant speech synthesis pipeline and has ...