Evaluating Parameter Sharing for Spoofing-Aware Speaker Verification: A Case Study on the ASVspoof 5 Dataset
| dc.contributor.author | Buker, Aykut | |
| dc.contributor.author | Kurnaz, Oguzhan | |
| dc.contributor.author | Bekiryazici, Yule | |
| dc.contributor.author | Demirtac, Selim Can | |
| dc.contributor.author | Hanilci, Cemal | |
| dc.date.accessioned | 2026-02-08T15:15:52Z | |
| dc.date.available | 2026-02-08T15:15:52Z | |
| dc.date.issued | 2025 | |
| dc.department | Bursa Teknik Üniversitesi | |
| dc.description | 2025 Interspeech Conference -- AUG 17-21, 2025 -- Rotterdam, NETHERLANDS | |
| dc.description.abstract | Spoofing-aware speaker verification (SASV) is an important but challenging task and has been a primary focus of the recently organized ASVspoof 5 challenge. As SASV integrates automatic speaker verification (ASV) and countermeasure (CM) systems, its performance depends on the effectiveness of each system. This study systematically examines the impact of different parameter-sharing (PS) strategies, which facilitate joint optimization, on SASV performance using the ASVspoof 5 dataset. Experimental results indicate that PS enhances performance for specific attack types and codec conditions. For example, the baseline system achieves a min a-DCF of 0.329 on the A26 attack, which improves to 0.233 with PS. Similarly, for AMR-compressed signals, PS yields a 14.09% performance gain. These observations show that PS techniques are effective in mitigating certain spoofing attacks and improving robustness to degraded audio conditions in SASV systems. | |
| dc.description.sponsorship | Meta AI | |
| dc.identifier.doi | 10.21437/Interspeech.2025-2618 | |
| dc.identifier.endpage | 4577 | |
| dc.identifier.issn | 2308-457X | |
| dc.identifier.scopus | 2-s2.0-105020033134 | |
| dc.identifier.scopusquality | N/A | |
| dc.identifier.startpage | 4573 | |
| dc.identifier.uri | https://doi.org/10.21437/Interspeech.2025-2618 | |
| dc.identifier.uri | https://hdl.handle.net/20.500.12885/5997 | |
| dc.identifier.wos | WOS:001613931400339 | |
| dc.identifier.wosquality | N/A | |
| dc.indekslendigikaynak | Web of Science | |
| dc.indekslendigikaynak | Scopus | |
| dc.language.iso | en | |
| dc.publisher | Isca-Int Speech Communication Assoc | |
| dc.relation.ispartof | Interspeech 2025 | |
| dc.relation.publicationcategory | Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı | |
| dc.rights | info:eu-repo/semantics/closedAccess | |
| dc.snmz | WOS_KA_20260207 | |
| dc.subject | spoofing-aware speaker verification | |
| dc.subject | parameter sharing | |
| dc.subject | ASVspoof | |
| dc.title | Evaluating Parameter Sharing for Spoofing-Aware Speaker Verification: A Case Study on the ASVspoof 5 Dataset | |
| dc.type | Conference Object |












