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

Abstract

Recently, denoising diffusion probabilistic models and generative score matching have shown high potential in modelling complex data distributions while stochastic calculus has provided a unified point of view on these techniques allowing for flexible inference schemes. In this paper we introduce Grad-TTS, a novel text-to-speech model with score-based decoder producing mel-spectrograms by gradually transforming noise predicted by encoder and aligned with text input by means of Monotonic Alignment Search. The framework of stochastic differential equations helps us to generalize conventional diffusion probabilistic models to the case of reconstructing data from noise with different parameters and allows to make this reconstruction flexible by explicitly controlling trade-off between sound quality and inference speed. Subjective human evaluation shows that Grad-TTS is competitive with state-of-the-art text-to-speech approaches in terms of Mean Opinion Score. We will make the code publicly available shortly.

References in corpus (8)

• WaveNet: A Generative Model for Raw Audio
• Deep Unsupervised Learning using Nonequilibrium Thermodynamics
• Variational Inference with Normalizing Flows
• Generative Modeling by Estimating Gradients of the Data Distribution
• MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
• Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling
• Parallel Tacotron: Non-Autoregressive and Controllable TTS
• Diffusion models for Handwriting Generation

Cited by in corpus (8)

• A Survey on Neural Speech Synthesis
• Diffusion Schrödinger Bridge with Applications to Score-Based Generative Modeling
• On Fast Sampling of Diffusion Probabilistic Models
• Maximum Likelihood Training of Score-Based Diffusion Models
• UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding
• SegDiff: Image Segmentation with Diffusion Probabilistic Models
• Denoising Diffusion Gamma Models
• Bridge Diffusion Model: Bridge Chinese Text-to-Image Diffusion Model with English Communities