# Natural Yet Challenging to Detect: Robust In-the-Wild TTS through EMA and Dual-Scoring Prompt Selection -- Submission for WildSpoof 2026 TTS Track

Source: [Natural Yet Challenging to Detect: Robust In-the-Wild TTS through EMA and Dual-Scoring Prompt Selection -- Submission for WildSpoof 2026 TTS Track](<https://www.sota2.com/research/paper/6a13d7ad6f71c5ae7dc9eab7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-26T05:00:13.075Z

Authors: Renhe Sun, Jiayi Zhou, Haolin He, Yueying Feng, Jian Liu

Published: 2026-05-22T17:18:50.000Z

## Abstract

In this technical report, we describe our submission for the WildSpoof Challenge TTS Track: Text-to-Speech with In-the-Wild Data. We introduce F5-TTS-DPS, a model built upon the F5-TTS architecture. Our approach integrates Exponential Moving Average (EMA) into supervised fine-tuning to stabilize training and improve generalization. To enhance synthesis fidelity, we leverage large language models (LLMs) and large audio language models (LALMs) for dual-scoring prompt selection, filtering reference audio and text prompts to ensure quality while addressing alignment issues in noisy datasets.   Experimental evaluation demonstrates that F5-TTS-DPS achieves strong performance with UTMOS of 3.20 and speaker similarity of 0.51 on the development set. More importantly, our model achieves the best a-DCF scores of 0.1582, 0.5233, and 0.2562 across three advanced SASV systems among all submissions, indicating our synthesized speech is the most difficult to detect and exhibits the highest degree of naturalness and authenticity. Combined with competitive WER performance, these results validate the effectiveness of our approach in generating natural-sounding speech with strong spoofing capabilities.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Text-to-Speech on WildSpoof Seen speakers 2026 (Evaluation)](<https://www.sota2.com/research/sota/text-to-speech-on-wildspoof-seen-speakers-2026-evaluation.md>): Text-to-Speech; WildSpoof Seen speakers 2026 (Evaluation); UTMOS: 3.2016.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.23859>)

[PDF](<https://arxiv.org/pdf/2605.23859.pdf>)
