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

TL;DR

This paper introduces a robust TTS training method using Self-Purifying Flow Matching to adapt an open-weight TTS model for in-the-wild speech, achieving top performance in the WildSpoof Challenge.

Contribution

The paper proposes a novel fine-tuning approach with SPFM that improves robustness of open-weight TTS models to real-world noisy speech conditions.

Findings

Achieved lowest Word Error Rate among competitors.

Ranked second in perceptual quality metrics.

Demonstrated effective adaptation of open-weight models to diverse speech data.

Abstract

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, \textit{Supertonic}\footnote{\url{https://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.