# VoiceRestore: Flow-Matching Transformers for Speech Recording Quality Restoration

arXiv: https://arxiv.org/abs/2501.00794 · HTML: https://mlsanity.com/paper/2501.00794/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 0 of its 14 references that are in the map.
- First posted on arXiv 1 Jan 2025.

## Placed in

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

## Built on by (most cited first, 2 of 2)

- [Balalaika: Data-Centric, Prosody-Aware Annotation Pipeline for Russian Speech](https://mlsanity.com/paper/2507.13563/) (2025)
- [SB-RF: Schr"odinger Bridge Rectified Flow for One-Step Robust Speech Enhancement](https://mlsanity.com/paper/2606.05575/) (2026)

## Abstract (arXiv)

We present VoiceRestore, a novel approach to restoring the quality of speech recordings using flow-matching Transformers trained in a self-supervised manner on synthetic data. Our method tackles a wide range of degradations frequently found in both short and long-form speech recordings, including background noise, reverberation, compression artifacts, and bandwidth limitations - all within a single, unified model. Leveraging conditional flow matching and classifier free guidance, the model learns to map degraded speech to high quality recordings without requiring paired clean and degraded datasets. We describe the training process, the conditional flow matching framework, and the model's architecture. We also demonstrate the model's generalization to real-world speech restoration tasks, including both short utterances and extended monologues or dialogues. Qualitative and quantitative evaluations show that our approach provides a flexible and effective solution for enhancing the quality of speech recordings across varying lengths and degradation types.