# CogSR: Semantic-Aware Speech Super-Resolution via Chain-of-Thought Guided Flow Matching

arXiv: https://arxiv.org/abs/2512.16304 · HTML: https://mlsanity.com/paper/2512.16304/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 18 Dec 2025.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 19 of 19)

- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [Qwen2-Audio Technical Report](https://mlsanity.com/paper/2407.10759/) (2024)
- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [Fast Timing-Conditioned Latent Audio Diffusion](https://mlsanity.com/paper/2402.04825/) (2024)
- [Matcha-TTS: A fast TTS architecture with conditional flow matching](https://mlsanity.com/paper/2309.03199/) (2023)
- [VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching](https://mlsanity.com/paper/2309.05027/) (2023)
- [AudioSR: Versatile Audio Super-resolution at Scale](https://mlsanity.com/paper/2309.07314/) (2023)
- [Neural Vocoder is All You Need for Speech Super-resolution](https://mlsanity.com/paper/2203.14941/) (2022)
- [VoiceFixer: A Unified Framework for High-Fidelity Speech Restoration](https://mlsanity.com/paper/2204.05841/) (2022)
- [FlowSE: Efficient and High-Quality Speech Enhancement via Flow Matching](https://mlsanity.com/paper/2505.19476/) (2025)
- [Thinking with Sound: Audio Chain-of-Thought Enables Multimodal Reasoning in Large Audio-Language Models](https://mlsanity.com/paper/2509.21749/) (2025)
- [Hallucination Benchmark for Speech Foundation Models](https://mlsanity.com/paper/2510.16567/) (2025)
- [SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought](https://mlsanity.com/paper/2505.24181/) (2025)
- [mdctGAN: Taming transformer-based GAN for speech super-resolution with Modified DCT spectra](https://mlsanity.com/paper/2305.11104/) (2023)
- [SAGA-SR: Semantically and Acoustically Guided Audio Super-Resolution](https://mlsanity.com/paper/2509.24924/) (2025)
- [HiFi-SR: A Unified Generative Transformer-Convolutional Adversarial Network for High-Fidelity Speech Super-Resolution](https://mlsanity.com/paper/2501.10045/) (2025)

## Abstract (arXiv)

Applying speech super-resolution (SR) to recordings with severely low sampling rates is a critical challenge in digital archiving and investigative audio recovery. In these scenarios, the input lacks essential acoustic cues. Consequently, existing generative models often fail; without sufficient context, they hallucinate phonetic content, guessing words based on probability rather than meaning. To address this, we propose CogSR, a framework designed specifically for high-precision, offline restoration. Our approach shifts the focus from simple signal mapping to cognitive reconstruction. By integrating a Large Audio-Language Model, we employ Chain-of-Thought reasoning to act as a semantic anchor, while explicit acoustic priors ensure the speaker's identity remains consistent. This guides a Rectified Flow backbone to synthesize high-frequency details that are not only realistic but linguistically accurate. Evaluations show that CogSR effectively eliminates ambiguity in severe degradation regimes, making it a robust solution for restoring high-value legacy and surveillance audio.