Universr: Unified And Versatile Audio Super-resolution Via Vocoder-free Flow Matching

Abstract

In this paper, we present a vocoder-free framework for audio super-resolution that employs a flow matching generative model to capture the conditional distribution of complex-valued spectral coefficients. Unlike conventional two-stage diffusion-based approaches that predict a mel-spectrogram and then rely on a pre-trained neural vocoder to synthesize waveforms, our method directly reconstructs waveforms via the inverse Short-Time Fourier Transform (iSTFT), thereby eliminating the dependence on a separate vocoder. This design not only simplifies end-to-end optimization but also overcomes a critical bottleneck of two-stage pipelines, where the final audio quality is fundamentally constrained by vocoder performance. Experiments show that our model consistently produces high-fidelity 48 kHz audio across diverse upsampling factors, achieving state-of-the-art performance on both speech and general audio datasets.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keychoi2025universr

Related papers

• Flowhigh: Towards Efficient And High-quality Audio Super-resolution With Single-step Flow Matching (2025)5.84
• Inspiremusic: Integrating Super Resolution And Large Language Model For High-fidelity Long-form Music Generation (2025)6.26
• Neural Vocoder Is All You Need For Speech Super-resolution (2022)12.25
• Audio Dequantization For High Fidelity Audio Generation In Flow-based Neural Vocoder (2020)6.77
• Real-time And Accurate: Zero-shot High-fidelity Singing Voice Conversion With Multi-condition Flow Synthesis (2024)0.00
• Flashsr: One-step Versatile Audio Super-resolution Via Diffusion Distillation (2025)4.52
• STSR: High-fidelity Speech Super-resolution Via Spectral-transient Context Modeling (2025)0.00
• V2sflow: Video-to-speech Generation With Speech Decomposition And Rectified Flow (2024)8.52