Robust TTS Training via Self-Purifying Flow Matching for the WildSpoof 2026 TTS Track
This addresses the problem of adapting TTS systems to noisy real-world conditions for speech synthesis applications, though it is incremental as it builds on existing models and techniques.
The paper tackled robust text-to-speech adaptation for in-the-wild speech by fine-tuning an open-weight TTS model with Self-Purifying Flow Matching to handle label noise, achieving the lowest Word Error Rate among all teams in the WildSpoof Challenge while ranking second in perceptual metrics.
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.