Wavefit: An Iterative And Non-autoregressive Neural Vocoder Based On Fixed-point Iteration

Abstract

Denoising diffusion probabilistic models (DDPMs) and generative adversarial networks (GANs) are popular generative models for neural vocoders. The DDPMs and GANs can be characterized by the iterative denoising framework and adversarial training, respectively. This study proposes a fast and high-quality neural vocoder called \textit\{WaveFit\}, which integrates the essence of GANs into a DDPM-like iterative framework based on fixed-point iteration. WaveFit iteratively denoises an input signal, and trains a deep neural network (DNN) for minimizing an adversarial loss calculated from intermediate outputs at all iterations. Subjective (side-by-side) listening tests showed no statistically significant differences in naturalness between human natural speech and those synthesized by WaveFit with five iterations. Furthermore, the inference speed of WaveFit was more than 240 times faster than WaveRNN. Audio demos are available at \url\{google.github.io/df-conformer/wavefit/\}.

Stats

• citations17
• S2 citations—
• github stars0
• HF likes0
• heat score9.41
• arxiv keykoizumi2022wavefit

Related papers

• Diffwave: A Versatile Diffusion Model For Audio Synthesis (2020)0.00
• Wave-u-net Discriminator: Fast And Lightweight Discriminator For Generative Adversarial Network-based Speech Synthesis (2023)6.34
• Periodgrad: Towards Pitch-controllable Neural Vocoder Based On A Diffusion Probabilistic Model (2024)0.00
• High-fidelity And Low-latency Universal Neural Vocoder Based On Multiband Wavernn With Data-driven Linear Prediction For Discrete Waveform Modeling (2021)6.77
• Fastfit: Towards Real-time Iterative Neural Vocoder By Replacing U-net Encoder With Multiple Stfts (2023)0.00
• Diffar: Denoising Diffusion Autoregressive Model For Raw Speech Waveform Generation (2023)0.00
• Generative Adversarial Network Based Speaker Adaptation For High Fidelity Wavenet Vocoder (2018)5.84
• Specgrad: Diffusion Probabilistic Model Based Neural Vocoder With Adaptive Noise Spectral Shaping (2022)11.49