Saved in:
Bibliographic Details
Main Authors: Singh, Robin, Nair, Aditya Yogesh, Palumbo, Fabio, Barbaro, Florian, Dyka, Anna, Rachakonda, Lohith
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.20510
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914286488518656
author Singh, Robin
Nair, Aditya Yogesh
Palumbo, Fabio
Barbaro, Florian
Dyka, Anna
Rachakonda, Lohith
author_facet Singh, Robin
Nair, Aditya Yogesh
Palumbo, Fabio
Barbaro, Florian
Dyka, Anna
Rachakonda, Lohith
contents Recent advances in Text-to-Speech (TTS) systems have substantially increased the realism of synthetic speech, raising new challenges for audio deepfake detection. This work presents a comparative evaluation of three state-of-the-art TTS models--Dia2, Maya1, and MeloTTS--representing streaming, LLM-based, and non-autoregressive architectures. A corpus of 12,000 synthetic audio samples was generated using the Daily-Dialog dataset and evaluated against four detection frameworks, including semantic, structural, and signal-level approaches. The results reveal significant variability in detector performance across generative mechanisms: models effective against one TTS architecture may fail against others, particularly LLM-based synthesis. In contrast, a multi-view detection approach combining complementary analysis levels demonstrates robust performance across all evaluated models. These findings highlight the limitations of single-paradigm detectors and emphasize the necessity of integrated detection strategies to address the evolving landscape of audio deepfake threats.
format Preprint
id arxiv_https___arxiv_org_abs_2601_20510
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Audio Deepfake Detection in the Age of Advanced Text-to-Speech models
Singh, Robin
Nair, Aditya Yogesh
Palumbo, Fabio
Barbaro, Florian
Dyka, Anna
Rachakonda, Lohith
Sound
Artificial Intelligence
Audio and Speech Processing
Recent advances in Text-to-Speech (TTS) systems have substantially increased the realism of synthetic speech, raising new challenges for audio deepfake detection. This work presents a comparative evaluation of three state-of-the-art TTS models--Dia2, Maya1, and MeloTTS--representing streaming, LLM-based, and non-autoregressive architectures. A corpus of 12,000 synthetic audio samples was generated using the Daily-Dialog dataset and evaluated against four detection frameworks, including semantic, structural, and signal-level approaches. The results reveal significant variability in detector performance across generative mechanisms: models effective against one TTS architecture may fail against others, particularly LLM-based synthesis. In contrast, a multi-view detection approach combining complementary analysis levels demonstrates robust performance across all evaluated models. These findings highlight the limitations of single-paradigm detectors and emphasize the necessity of integrated detection strategies to address the evolving landscape of audio deepfake threats.
title Audio Deepfake Detection in the Age of Advanced Text-to-Speech models
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2601.20510