Metraipolis › archive › dc_ba210ef6688d
Spooftral: Can Voxtral Audio-Language Model Detect Speech Spoofing? — arXiv:2609.28713
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.28713
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T04:50:08.554Z
- SHA-256 of the archived text
c74a413c83da129eb3f01b42327e4bf7304eb536e96b3551fc02a6ee7df006e4- Stable URL of this page
https://metraipolis.com/documento/dc_ba210ef6688d
How to cite
Spooftral: Can Voxtral Audio-Language Model Detect Speech Spoofing? — arXiv:2609.28713 — arXiv (en), https://arxiv.org/abs/2609.28713 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ba210ef6688d (Metraipolis archive dc_ba210ef6688d, sha256 c74a413c83da129eb3f01b42327e4bf7304eb536e96b3551fc02a6ee7df006e4)
BibTeX
@misc{dcba210ef6688d,
title = {Spooftral: Can Voxtral Audio-Language Model Detect Speech Spoofing? — arXiv:2609.28713},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.28713},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ba210ef6688d; sha256 c74a413c83da129eb3f01b42327e4bf7304eb536e96b3551fc02a6ee7df006e4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28713. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Self-supervised learning (SSL) countermeasures (CMs) have shown strong performance in recent years. However, they often show degraded performance while facing unseen spoofing attacks and mismatched conditions. This study examines the Voxtral audio-language model (ALM) framework for spoofing detection, as a step toward combining CM capabilities within the ALM framework. We analyze how Voxtral captures spoofing cues through audio-text processing and propose an instruction-guided approach that uses label-sequence likelihoods to evaluate bonafide and spoofed speech. Experiments on the ASVspoof databases show that without task-specific adaptation, the LLM layers emphasize semantic representations, reducing the separability of spoof-discriminative acoustic cues compared to the Whisper-based audio encoder. Consequently, spoofing-related information becomes less separable after language-model processing. We also applied lightweight adaptation using weight-decomposed low-rank adaptation (DoRA) to the Voxtral model and propose the Spooftral model, achieving an equal error rate (EER) of 4.25% on the ASVspoof5 evaluation set. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.CL). Categorie arXiv: Audio and Speech Processing (eess.AS) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.28713 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T04:27:20.146Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).