Avocodo: Generative Adversarial Network For Artifact-free Vocoder

Abstract

Neural vocoders based on the generative adversarial neural network (GAN) have been widely used due to their fast inference speed and lightweight networks while generating high-quality speech waveforms. Since the perceptually important speech components are primarily concentrated in the low-frequency bands, most GAN-based vocoders perform multi-scale analysis that evaluates downsampled speech waveforms. This multi-scale analysis helps the generator improve speech intelligibility. However, in preliminary experiments, we discovered that the multi-scale analysis which focuses on the low-frequency bands causes unintended artifacts, e.g., aliasing and imaging artifacts, which degrade the synthesized speech waveform quality. Therefore, in this paper, we investigate the relationship between these artifacts and GAN-based vocoders and propose a GAN-based vocoder, called Avocodo, that allows the synthesis of high-fidelity speech with reduced artifacts. We introduce two kinds of discriminators to

Stats

• citations17
• S2 citations—
• github stars0
• HF likes0
• heat score9.41
• arxiv keybak2022avocodo

Related papers

• Vocgan: A High-fidelity Real-time Vocoder With A Hierarchically-nested Adversarial Network (2020)12.54
• Vnet: A Gan-based Multi-tier Discriminator Network For Speech Synthesis Vocoders (2024)2.26
• Adavocoder: Adaptive Vocoder For Custom Voice (2022)2.26
• A Post Auto-regressive GAN Vocoder Focused On Spectrum Fracture (2022)0.00
• Bigvgan: A Universal Neural Vocoder With Large-scale Training (2022)6.17
• Multi-scale Sub-band Constant-q Transform Discriminator For High-fidelity Vocoder (2023)0.00
• Analysis By Adversarial Synthesis -- A Novel Approach For Speech Vocoding (2019)3.58
• Training Generative Adversarial Network-based Vocoder With Limited Data Using Augmentation-conditional Discriminator (2024)2.26