Accelerating High-fidelity Waveform Generation Via Adversarial Flow Matching Optimization

Abstract

This paper introduces PeriodWave-Turbo, a high-fidelity and high-efficient waveform generation model via adversarial flow matching optimization. Recently, conditional flow matching (CFM) generative models have been successfully adopted for waveform generation tasks, leveraging a single vector field estimation objective for training. Although these models can generate high-fidelity waveform signals, they require significantly more ODE steps compared to GAN-based models, which only need a single generation step. Additionally, the generated samples often lack high-frequency information due to noisy vector field estimation, which fails to ensure high-frequency reproduction. To address this limitation, we enhance pre-trained CFM-based generative models by incorporating a fixed-step generator modification. We utilized reconstruction losses and adversarial feedback to accelerate high-fidelity waveform generation. Through adversarial flow matching optimization, it only requires 1,000 steps of

Stats

• citations0
• S2 citations—
• github stars220
• HF likes0
• heat score4.69
• arxiv keylee2024accelerating

Related papers

• Periodwave: Multi-period Flow Matching For High-fidelity Waveform Generation (2024)4.69
• Parallel Wavegan: A Fast Waveform Generation Model Based On Generative Adversarial Networks With Multi-resolution Spectrogram (2019)0.00
• Probability Density Distillation With Generative Adversarial Networks For High-quality Parallel Waveform Generation (2019)10.48
• Generative Pre-training For Speech With Flow Matching (2023)0.00
• Melgan: Generative Adversarial Networks For Conditional Waveform Synthesis (2019)0.00
• TFGAN: Time And Frequency Domain Based Generative Adversarial Network For High-fidelity Speech Synthesis (2020)0.00
• Chunked Autoregressive GAN For Conditional Waveform Synthesis (2021)0.00
• Flowmac: Conditional Flow Matching For Audio Coding At Low Bit Rates (2024)0.00