WaveFM: A High-Fidelity and Efficient Vocoder Based on Flow Matching

📅 2025-03-20
📈 Citations: 0
Influential: 0
📄 PDF

career value

205K/year
🤖 AI Summary
Flow Matching (FM) degrades audio quality when directly applied to neural vocoders. To address this, we propose WaveFM—a flow-matching-based reparameterized vocoder tailored for mel-spectrogram–conditioned speech synthesis. Our key contributions are: (1) a mel-conditional prior distribution replacing the standard isotropic Gaussian prior; (2) a multi-resolution short-time Fourier transform (STFT) auxiliary loss to improve time-frequency fidelity; and (3) consistency distillation enabling high-fidelity one-step waveform generation. Experiments demonstrate that WaveFM consistently outperforms state-of-the-art diffusion-based vocoders in naturalness (MOS), synthesis quality, and inference speed. On benchmarks including LJSpeech, WaveFM achieves single-step inference with perceptual quality comparable to multi-step sampling, while accelerating inference by over an order of magnitude.

Technology Category

Application Category

📝 Abstract
Flow matching offers a robust and stable approach to training diffusion models. However, directly applying flow matching to neural vocoders can result in subpar audio quality. In this work, we present WaveFM, a reparameterized flow matching model for mel-spectrogram conditioned speech synthesis, designed to enhance both sample quality and generation speed for diffusion vocoders. Since mel-spectrograms represent the energy distribution of waveforms, WaveFM adopts a mel-conditioned prior distribution instead of a standard Gaussian prior to minimize unnecessary transportation costs during synthesis. Moreover, while most diffusion vocoders rely on a single loss function, we argue that incorporating auxiliary losses, including a refined multi-resolution STFT loss, can further improve audio quality. To speed up inference without degrading sample quality significantly, we introduce a tailored consistency distillation method for WaveFM. Experiment results demonstrate that our model achieves superior performance in both quality and efficiency compared to previous diffusion vocoders, while enabling waveform generation in a single inference step.
Problem

Research questions and friction points this paper is trying to address.

Enhances audio quality in flow matching vocoders
Reduces unnecessary transportation costs in synthesis
Improves generation speed without quality degradation
Innovation

Methods, ideas, or system contributions that make the work stand out.

Reparameterized flow matching for speech synthesis
Mel-conditioned prior distribution reduces transportation costs
Consistency distillation speeds up inference without quality loss
🔎 Similar Papers
No similar papers found.