Extraction of Novel Features Based on Histograms of MFCCs Used in Emotion Classification from Generated Original Speech Dataset

Basit Öğe Kaydı
dc.authoridAtmis, Mahir/0000-0002-9377-6224
dc.authorwosidAtmis, Mahir/AAA-1862-2021
dc.contributor.authorPakyurek, Muhammet
dc.contributor.authorAtmis, Mahir
dc.contributor.authorKulac, Selman
dc.contributor.authorUludag, Umut
dc.date.accessioned2021-12-01T18:49:18Z
dc.date.available2021-12-01T18:49:18Z
dc.date.issued2020
dc.department[Belirlenecek]en_US
dc.description.abstractThis paper introduces two significant contributions: one is a new feature based on histograms of MFCC (Mel-Frequency Cepstral Coefficients) extracted from the audio files that can be used in emotion classification from speech signals, and the other - our new multi-lingual and multi-personal speech database, which has three emotions. In this study, Berlin Database (BD) (in German) and our custom PAU database (in English) created from YouTube videos and popular TV shows are employed to train and evaluate the test results. Experimental results show that our proposed features lead to better classification of results than the current state-of-the-art approaches with Support Vector Machine (SVM) from the literature. Thanks to our novel feature, this study can outperform a number of MFCC features and SVM classifier based studies, including recent researches. Due to the lack of our novel feature based approaches, one of the most common MFCC and SVM framework is implemented and one of the most common database Berlin DB is used to compare our novel approach with these kind of approaches.en_US
dc.identifier.doi10.5755/j01.eie.26.1.25309
dc.identifier.endpage51en_US
dc.identifier.issn1392-1215
dc.identifier.issue1en_US
dc.identifier.scopus2-s2.0-85082514166en_US
dc.identifier.scopusqualityQ3en_US
dc.identifier.startpage46en_US
dc.identifier.urihttps://doi.org/10.5755/j01.eie.26.1.25309
dc.identifier.urihttps://hdl.handle.net/20.500.12684/10699
dc.identifier.volume26en_US
dc.identifier.wosWOS:000518114800007en_US
dc.identifier.wosqualityQ4en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherKaunas Univ Technologyen_US
dc.relation.ispartofElektronika Ir Elektrotechnikaen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectEmotion classificationen_US
dc.subjectMFCCen_US
dc.subjectSVMen_US
dc.subjectSpeech signalen_US
dc.subjectRecognitionen_US
dc.titleExtraction of Novel Features Based on Histograms of MFCCs Used in Emotion Classification from Generated Original Speech Dataseten_US
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
10699.pdf
Boyut:
1.2 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu