Fastdiff: A Fast Conditional Diffusion Model For High-quality Speech Synthesis
2022 · Rongjie Huang, Max W. Y. Lam, Jun Wang, et al.
Abstract
Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hindered their applications to speech synthesis. This paper proposes FastDiff, a fast conditional diffusion model for high-quality speech synthesis. FastDiff employs a stack of time-aware location-variable convolutions of diverse receptive field patterns to efficiently model long-term time dependencies with adaptive conditions. A noise schedule predictor is also adopted to reduce the sampling steps without sacrificing the generation quality. Based on FastDiff, we design an end-to-end text-to-speech synthesizer, FastDiff-TTS, which generates high-fidelity speech waveforms without any intermediate feature (e.g., Mel-spectrogram). Our evaluation of FastDiff demonstrates the state-of-the-art results with higher-quality (MOS 4.28) speech samples. Also, FastDiff enables a sampling speed of 58x faster than real-time on a
Authors
(none)
Tags
Stats
Related papers
- Prodiff: Progressive Fast Diffusion Model For High-quality Text-to-speech (2022)0.00
- Diffgan-tts: High-fidelity And Efficient Text-to-speech With Denoising Diffusion Gans (2022)0.00
- BDDM: Bilateral Denoising Diffusion Models For Fast And High-quality Speech Synthesis (2022)4.76
- Diffar: Denoising Diffusion Autoregressive Model For Raw Speech Waveform Generation (2023)0.00
- Resgrad: Residual Denoising Diffusion Probabilistic Models For Text To Speech (2022)0.00
- Adversarial Training Of Denoising Diffusion Model Using Dual Discriminators For High-fidelity Multi-speaker TTS (2023)2.26
- Diffprosody: Diffusion-based Latent Prosody Generation For Expressive Speech Synthesis With Prosody Conditional Adversarial Training (2023)10.07
- Speaking In Wavelet Domain: A Simple And Efficient Approach To Speed Up Speech Diffusion Model (2024)5.24