Angular Margin Softmax Loss and Its Variants for Double Compressed AMR Audio Detection

Basit Öğe Kaydı
dc.authorid0000-0002-6404-1499en_US
dc.authorid0000-0002-9174-0367en_US
dc.authorscopusid57215422993en_US
dc.authorscopusid35781455400en_US
dc.contributor.authorBüker, Aykut
dc.contributor.authorHanilçi, Cemal
dc.date.accessioned2022-04-01T12:04:13Z
dc.date.available2022-04-01T12:04:13Z
dc.date.issued2021en_US
dc.departmentBTÜ, Mühendislik ve Doğa Bilimleri Fakültesi, Elektrik-Elektronik Mühendisliği Bölümüen_US
dc.description.abstractDouble compressed (DC) adaptive multi-rate (AMR) audio detection is an important but challenging audio forensic task which has received great attention over the last decade. Although the majority of the existing studies extract hand-crafted features and classify these features using traditional pattern matching algorithms such as support vector machines (SVM), recently convolutional neural network (CNN) based DC AMR audio detection system was proposed which yields very promising detection performance. Similar to any traditional CNN based classification system, CNN based DC AMR recognition system uses standard softmax loss as the training criterion. In this paper, we propose to use angular margin softmax loss and its variants for DC AMR detection problem. Although using angular margin softmax was originally proposed for face recognition, we adapt it to the CNN based end-to-end DC audio detection system. The angular margin softmax basically introduces a margin between two classes so that the system can learn more discriminative embeddings for the problem. Experimental results show that adding angular margin penalty to the traditional softmax loss increases the average DC AMR audio detection from 95.83% to 100%. It is also found that the angular margin softmax loss functions boost the DC AMR audio detection performance when there is a mismatch between training and test datasets.en_US
dc.identifier.doi10.1145/3437880.3460414en_US
dc.identifier.endpage50en_US
dc.identifier.isbn978-145038295-3
dc.identifier.scopusqualityN/Aen_US
dc.identifier.startpage45en_US
dc.identifier.urihttps://hdl.handle.net/20.500.12885/1843
dc.indekslendigikaynakScopusen_US
dc.institutionauthorBüker, Aykut
dc.institutionauthorHanilçi, Cemal
dc.language.isoenen_US
dc.publisherAssociation for Computing Machinery, Incen_US
dc.relation.ispartofIH and MMSec 2021 - Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Securityen_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectangular margin softmax lossen_US
dc.subjectcnnen_US
dc.subjectdouble compressed amr audio detectionen_US
dc.titleAngular Margin Softmax Loss and Its Variants for Double Compressed AMR Audio Detectionen_US
dc.typeConference Objecten_US

Dosyalar

Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu
Elektrik Elektronik Mühendisliği Bölümü Yayın Koleksiyonu