Fine-Tuning ECAPA-TDNN For Turkish Speaker Verification

Basit Öğe Kaydı
dc.contributor.authorDemirtaş, Selim Can
dc.contributor.authorHanilçi, Cemal
dc.date.accessioned2026-02-08T15:11:12Z
dc.date.available2026-02-08T15:11:12Z
dc.date.issued2024
dc.departmentBursa Teknik Üniversitesi
dc.description8th International Artificial Intelligence and Data Processing Symposium, IDAP 2024 -- 2024-09-21 through 2024-09-22 -- Malatya -- 203423
dc.description.abstractCompared to Turkish speech databases, English speech databases are significantly larger, featuring many more speakers. This creates a trade-off between data adequacy and language for Turkish ASV systems. This paper explores this trade-off by comparing three different approaches using the state-of-the-art ECAPA-TDNN model: utilizing the pre-trained English ECAPA-TDNN model, training the ECAPA-TDNN model from scratch with the Turkish Common Voice dataset, and fine-tuning the pre-trained English ECAPA-TDNN model with Turkish data. Experimental results reveal that the pre-trained English ECAPA-TDNN model outperforms the model trained from scratch on Turkish data and the fine-tuned model in terms of the equal error rate (EER) criterion. However, the fine-tuning approach demonstrates the best performance according to the minimum detection cost function (min-DCF) metric when security is prioritized over user convenience. © 2024 IEEE.
dc.identifier.doi10.1109/IDAP64064.2024.10710963
dc.identifier.isbn9798331531492
dc.identifier.scopus2-s2.0-85207867739
dc.identifier.scopusqualityN/A
dc.identifier.urihttps://doi.org/10.1109/IDAP64064.2024.10710963
dc.identifier.urihttps://hdl.handle.net/20.500.12885/5310
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzScopus_KA_20260207
dc.subjectautomatic speaker verification
dc.subjectfine-tuning
dc.titleFine-Tuning ECAPA-TDNN For Turkish Speaker Verification
dc.typeConference Object

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu