Source-Filter-Based Generative Adversarial Neural Vocoder for High Fidelity Speech Synthesis

Abstract

This paper proposes a source-filter-based generative adversarial neural vocoder named SF-GAN, which achieves high-fidelity waveform generation from input acoustic features by introducing F0-based source excitation signals to a neural filter framework. The SF-GAN vocoder is composed of a source module and a resolution-wise conditional filter module and is trained based on generative adversarial strategies. The source module produces an excitation signal from the F0 information, then the resolution-wise convolutional filter module combines the excitation signal with processed acoustic features at various temporal resolutions and finally reconstructs the raw waveform. The experimental results show that our proposed SF-GAN vocoder outperforms the state-of-the-art HiFi-GAN and Fre-GAN in both analysis-synthesis (AS) and text-to-speech (TTS) tasks, and the synthesized speech quality of SF-GAN is comparable to the ground-truth audio.

arXiv commentAccepted by NCMMSC 2022

References in corpus (5)

• MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
• SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
• High Fidelity Speech Synthesis with Adversarial Networks
• A Neural Vocoder with Hierarchical Generation of Amplitude and Phase Spectra for Statistical Parametric Speech Synthesis
• Quasi-Periodic Parallel WaveGAN: A Non-autoregressive Raw Waveform Generative Model with Pitch-dependent Dilated Convolution Neural Network