# SAGA-SR: Semantically and Acoustically Guided Audio Super-Resolution

arXiv: https://arxiv.org/abs/2509.24924 · HTML: https://mlsanity.com/paper/2509.24924/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Sep 2025.

## Built on by (most cited first, 4 of 4)

- [CogSR: Semantic-Aware Speech Super-Resolution via Chain-of-Thought Guided Flow Matching](https://mlsanity.com/paper/2512.16304/) (2025)
- [PF-D2M: A Pose-free Diffusion Model for Universal Dance-to-Music Generation](https://mlsanity.com/paper/2601.15872/) (2026)
- [P2Flow: Phoneme-aware Progressive Flow Matching for Extreme Speech Super-Resolution](https://mlsanity.com/paper/2609.24138/) (2026)
- [End-to-End Historical Music Restoration in Latent Space](https://mlsanity.com/paper/2610.00607/) (2026)

## Abstract (arXiv)

Versatile audio super-resolution (SR) aims to predict high-frequency components from low-resolution audio across diverse domains such as speech, music, and sound effects. Existing diffusion-based SR methods often fail to produce semantically aligned outputs and struggle with consistent high-frequency reconstruction. In this paper, we propose SAGA-SR, a versatile audio SR model that combines semantic and acoustic guidance. Based on a DiT backbone trained with a flow matching objective, SAGA-SR is conditioned on text and spectral roll-off embeddings. Due to the effective guidance provided by its conditioning, SAGA-SR robustly upsamples audio from arbitrary input sampling rates between 4 kHz and 32 kHz to 44.1 kHz. Both objective and subjective evaluations show that SAGA-SR achieves state-of-the-art performance across all test cases. Sound examples and code for the proposed model are available online.