# Robust TTS Training via Self-Purifying Flow Matching for the WildSpoof 2026 TTS Track

arXiv: https://arxiv.org/abs/2512.17293 · HTML: https://mlsanity.com/paper/2512.17293/

## 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 2 of its 3 references that are in the map.
- First posted on arXiv 19 Dec 2025.

## Placed in

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

## Builds on (most cited first, 2 of 2)

- [WildSpoof Challenge Evaluation Plan](https://mlsanity.com/paper/2508.16858/) (2025)
- [Training Flow Matching Models with Reliable Labels via Self-Purification](https://mlsanity.com/paper/2509.19091/) (2025)

## Abstract (arXiv)

This paper presents a lightweight text-to-speech (TTS) system developed for the WildSpoof Challenge TTS Track. Our approach fine-tunes the recently released open-weight TTS model, textitSupertonicfootnoteurlhttps://github.com/supertone-inc/supertonic, with Self-Purifying Flow Matching (SPFM) to enable robust adaptation to in-the-wild speech. SPFM mitigates label noise by comparing conditional and unconditional flow matching losses on each sample, routing suspicious text--speech pairs to unconditional training while still leveraging their acoustic information. The resulting model achieves the lowest Word Error Rate (WER) among all participating teams, while ranking second in perceptual metrics such as UTMOS and DNSMOS. These findings demonstrate that efficient, open-weight architectures like Supertonic can be effectively adapted to diverse real-world speech conditions when combined with explicit noise-handling mechanisms such as SPFM.