# Real-time Speech Restoration using Data Prediction Mean Flows

arXiv: https://arxiv.org/abs/2605.16251 · HTML: https://mlsanity.com/paper/2605.16251/

## 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 23 references that are in the map.
- First posted on arXiv 15 May 2026.

## Placed in

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

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

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Mean Flows for One-step Generative Modeling](https://mlsanity.com/paper/2505.13447/) (2025)
- [Stable Audio Open](https://mlsanity.com/paper/2407.14358/) (2024)
- [DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors](https://mlsanity.com/paper/2110.01763/) (2021)
- [Improved Mean Flows: On the Challenges of Fastforward Generative Models](https://mlsanity.com/paper/2512.02012/) (2025)
- [Universal Speech Enhancement with Score-based Diffusion](https://mlsanity.com/paper/2206.03065/) (2022)
- [EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation](https://mlsanity.com/paper/2406.06185/) (2024)
- [Interspeech 2021 Deep Noise Suppression Challenge](https://mlsanity.com/paper/2101.01902/) (2021)
- [ICASSP 2024 Speech Signal Improvement Challenge](https://mlsanity.com/paper/2401.14444/) (2024)
- [MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows](https://mlsanity.com/paper/2508.06098/) (2025)
- [Distillation and Pruning for Scalable Self-Supervised Representation-Based Speech Quality Assessment](https://mlsanity.com/paper/2502.05356/) (2025)
- [Diffusion Buffer: Online Diffusion-based Speech Enhancement with Sub-Second Latency](https://mlsanity.com/paper/2506.02908/) (2025)
- [MeanFlowSE: one-step generative speech enhancement via conditional mean flow](https://mlsanity.com/paper/2509.14858/) (2025)
- [Towards Real-Time Generative Speech Restoration with Flow-Matching](https://mlsanity.com/paper/2510.16997/) (2025)
- [MeanFlow-TSE: One-Step Generative Target Speaker Extraction with Mean Flow](https://mlsanity.com/paper/2512.18572/) (2025)
- [Real-Time Streamable Generative Speech Restoration with Flow Matching](https://mlsanity.com/paper/2512.19442/) (2025)

## Abstract (arXiv)

Generative models are capable to address difficult problems with non-unique solutions like bandwidth extension and gap filling, removing highly non-linear artifacts from codecs, clipping and distortion, as opposed to removing linear additive components like noise and reverb. While large offline processing models have shown impressive results, these tasks have not been solved with real-time capable models with low latency and compute. We propose a few-step flow matching model using Data Prediction Mean Flows in combination with suitable novel low-latency architecture to make flow matching models an attractive choice under theses constraints. Compared to state-of-the-art, our proposed mean flow model uses 120x less compute and introduces no algorithmic latency other than the STFT, while achieving similar audio quality.