Diff-TTS: A Denoising Diffusion Model for Text-to-Speech
arXiv:2104.01409
Abstract
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.
Submitted to INTERSPEECH 2021
References in corpus (17)
- Adam: A Method for Stochastic Optimization
- Denoising Diffusion Probabilistic Models
- Searching for Activation Functions
- HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
- FastSpeech: Fast, Robust and Controllable Text to Speech
- Improved Denoising Diffusion Probabilistic Models
- Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search
- Tacotron: Towards End-to-End Speech Synthesis
- DiffWave: A Versatile Diffusion Model for Audio Synthesis
- Denoising Diffusion Implicit Models
- Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning
- Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis
- ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech
- End-to-End Adversarial Text-to-Speech
- Non-Autoregressive Neural Text-to-Speech
- VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models
- EfficientTTS: An Efficient and High-Quality Text-to-Speech Architecture