SHDA: Sinkhorn Domain Attention for Cross-Domain Audio Anti-Spoofing

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F26%3A0199982" target="_blank" >RIV/00216305:26230/26:0199982 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/abstract/document/11024052" target="_blank" >https://ieeexplore.ieee.org/abstract/document/11024052</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TIFS.2025.3576576" target="_blank" >10.1109/TIFS.2025.3576576</a>

Jazyk výsledku

angličtina

Název v původním jazyce

SHDA: Sinkhorn Domain Attention for Cross-Domain Audio Anti-Spoofing

Popis výsledku v původním jazyce

Audio anti-spoofing algorithms struggle with fake samples from unseen spoofing techniques, even when trained with diverse data sets or data augmentation strategies. Unsupervised domain adaptation (UDA) algorithms have the potential to mitigate this challenge. Typically, UDA assumes that the source and target domains are distinct distributions with clear boundaries and seeks to align model representations between them. However, in anti-spoofing, various spoofing algorithms could cause the distributions of the generated samples to overlap, resulting in unclear domain boundaries. This hinders UDA algorithms from effectively measuring and aligning domain discrepancies. Moreover, forcibly aligning samples with significant discrepancies could diminish the model's discriminative capability. To solve this problem, we propose a domain attention algorithm with optimal transport (OT), termed Sinkhorn Domain Attention (SHDA). Unlike traditional attention mechanisms, SHDA identifies the optimal transfer plan by analyzing the global probability differences among cross-domain samples. Specifically, we first extract audio representations from various domains to compute the overall cost matrix between the source and target domains. Next, we employ Sinkhorn's iteration to calculate the OT coupling matrix, where cross-domain samples with minor differences receive higher transfer weights, while those with substantial differences receive lower weights. Finally, we use the coupling and cost matrices to compute the adaptation loss, effectively transferring the anti-spoofing model from multiple sources to the target domain. We conducted eight cross-domain experiments using eleven well-known anti-spoofing corpora. The results indicate that our label-free SHDA surpassed the state-of-the-art model by 40%.

Název v anglickém jazyce

SHDA: Sinkhorn Domain Attention for Cross-Domain Audio Anti-Spoofing

Popis výsledku anglicky

Audio anti-spoofing algorithms struggle with fake samples from unseen spoofing techniques, even when trained with diverse data sets or data augmentation strategies. Unsupervised domain adaptation (UDA) algorithms have the potential to mitigate this challenge. Typically, UDA assumes that the source and target domains are distinct distributions with clear boundaries and seeks to align model representations between them. However, in anti-spoofing, various spoofing algorithms could cause the distributions of the generated samples to overlap, resulting in unclear domain boundaries. This hinders UDA algorithms from effectively measuring and aligning domain discrepancies. Moreover, forcibly aligning samples with significant discrepancies could diminish the model's discriminative capability. To solve this problem, we propose a domain attention algorithm with optimal transport (OT), termed Sinkhorn Domain Attention (SHDA). Unlike traditional attention mechanisms, SHDA identifies the optimal transfer plan by analyzing the global probability differences among cross-domain samples. Specifically, we first extract audio representations from various domains to compute the overall cost matrix between the source and target domains. Next, we employ Sinkhorn's iteration to calculate the OT coupling matrix, where cross-domain samples with minor differences receive higher transfer weights, while those with substantial differences receive lower weights. Finally, we use the coupling and cost matrices to compute the adaptation loss, effectively transferring the anti-spoofing model from multiple sources to the target domain. We conducted eight cross-domain experiments using eleven well-known anti-spoofing corpora. The results indicate that our label-free SHDA surpassed the state-of-the-art model by 40%.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

IEEE Transactions on Information Forensics and Security

ISSN

1556-6013

e-ISSN

1556-6021

Svazek periodika

—

Číslo periodika v rámci svazku

20

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

16

Strana od-do

6474-6489

Kód UT WoS článku

001521429100006

EID výsledku v databázi Scopus

—