Fine-tuning Wav2Vec2 for Classification of Turkish Broadcast News and Advertisement Jingles

Simple item page
dc.authorscopusid57219836294
dc.authorscopusid58735257300
dc.authorscopusid57210943664
dc.authorscopusid58734530300
dc.authorscopusid55883747600
dc.contributor.authorDemirkiran,F.
dc.contributor.authorOner,O.
dc.contributor.authorKomecoglu,Y.
dc.contributor.authorGuven,R.
dc.contributor.authorKomecoglu,B.B.
dc.date.accessioned2024-06-23T21:38:38Z
dc.date.available2024-06-23T21:38:38Z
dc.date.issued2023
dc.departmentKadir Has Universityen_US
dc.department-tempDemirkiran F., Kadir Has University, Management Information Systems, Istanbul, Turkey; Oner O., Kodiks Bilişim A.Ş R&d Center, Istanbul, Turkey; Komecoglu Y., Kodiks Bilişim A.Ş R&d Center, Istanbul, Turkey; Guven R., Kodiks Bilişim A.Ş R&d Center, Istanbul, Turkey; Komecoglu B.B., Gebze Technical University, Computer Engineering, Kocaeli, Turkeyen_US
dc.description.abstractThe accurate classification of news and commercial jingles is essential for the automated generation of broadcast flow. Currently, in press companies, editors manually label the start and end times of news and advertisements, which incurs both cost and time loss. Although the method of extracting fingerprints of news and commercial jingles has been employed to detect jingles on a channel basis and automatically classify news and commercial music, this approach falls short when it comes to classifying new jingles produced by channels. In this study, we created a new dataset by extracting segments of commercial and news jingles from TV channels in Turkey. We analyzed the most effective second interval for classifying news or commercials, resulting in an impressive accuracy score of 98.18%. By leveraging this dataset and conducting extensive analysis, we have made significant progress in accurately classifying news and commercial jingles. This research can potentially save press companies costs and time by automating the classification process. © 2023 IEEE.en_US
dc.identifier.citation0
dc.identifier.doi10.1109/ASYU58738.2023.10296544
dc.identifier.isbn979-835030659-0
dc.identifier.scopus2-s2.0-85178315171
dc.identifier.scopusqualityN/A
dc.identifier.urihttps://doi.org/10.1109/ASYU58738.2023.10296544
dc.identifier.urihttps://hdl.handle.net/20.500.12469/5817
dc.identifier.wosqualityN/A
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartof2023 Innovations in Intelligent Systems and Applications Conference, ASYU 2023 -- 2023 Innovations in Intelligent Systems and Applications Conference, ASYU 2023 -- 11 October 2023 through 13 October 2023 -- Sivas -- 194153en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectadvertisingen_US
dc.subjectbinary classificationen_US
dc.subjectjingleen_US
dc.subjectnewsen_US
dc.subjectspeech classificationen_US
dc.subjectwav2vec2en_US
dc.titleFine-tuning Wav2Vec2 for Classification of Turkish Broadcast News and Advertisement Jinglesen_US
dc.typeConference Objecten_US
dspace.entity.typePublication

Files

Collections

Scopus İndeksli Yayınlar Koleksiyonu