Fusing Acoustic Feature Representations for Computational Paralinguistics Tasks

Basit Öğe Kaydı
dc.authorid0000-0003-3424-652X
dc.authorid0000-0001-7947-5508
dc.authorscopusid36241785000
dc.authorscopusid57219469958
dc.authorwosidKarpov, Alexey A/A-8905-2012
dc.authorwosidKAYA, Heysem/V-4493-2019
dc.contributor.authorKaya, Heysem
dc.contributor.authorKarpov, Alexey A.
dc.date.accessioned2022-05-11T14:15:49Z
dc.date.available2022-05-11T14:15:49Z
dc.date.issued2016
dc.departmentFakülteler, Çorlu Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü
dc.description17th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2016) -- SEP 08-12, 2016 -- San Francisco, CA
dc.description.abstractThe field of Computational Paralinguistics is rapidly growing and is of interest in various application domains ranging from biomedical engineering to forensics. The INTERSPEECH ComParE challenge series has a field-leading role, introducing novel problems with a common benchmark protocol for comparability. In this work, we tackle all three ComParE 2016 Challenge corpora (Native Language, Sincerity and Deception) benefiting from multi-level normalization on features followed by fast and robust kernel learning methods. Moreover, we employ computer vision inspired low level descriptor representation methods such as the Fisher vector encoding. After nonlinear preprocessing, obtained Fisher vectors are kernelized and mapped to target variables by classifiers based on Kernel Extreme Learning Machines and Partial Least Squares regression. We finally combine predictions of models trained on popularly used functional based descriptor encoding (openSMILE features) with those obtained from the Fisher vector encoding. In the preliminary experiments, our approach has significantly outperformed the baseline systems for Native Language and Sincerity sub-challenges both in the development and test sets.
dc.description.sponsorshipapple, amazon alexa, Google, Microsoft, ebay, facebook, YAHOO JAPAN, Baidu Res, IBM Res, CIRRUS LOGIC, DATATANG, NUANCE, Speechocean Ltd, Yandex, Raytheon Technol
dc.description.sponsorshipRussian Foundation for Basic ResearchRussian Foundation for Basic Research (RFBR) [16-37-60100]
dc.description.sponsorshipThis research is financially supported by the Russian Foundation for Basic Research (project Ns 16-37-60100).
dc.identifier.doi10.21437/Interspeech.2016-995
dc.identifier.endpage2050
dc.identifier.isbn978-1-5108-3313-5
dc.identifier.issn2308-457X
dc.identifier.scopus2-s2.0-84994384423
dc.identifier.scopusqualityN/A
dc.identifier.startpage2046
dc.identifier.urihttps://doi.org/10.21437/Interspeech.2016-995
dc.identifier.urihttps://hdl.handle.net/20.500.11776/6081
dc.identifier.wosWOS:000409394401111
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.institutionauthorKaya, Heysem
dc.language.isoen
dc.publisherIsca-Int Speech Communication Assoc
dc.relation.ispartof17th Annual Conference of the International Speech Communication Association (Interspeech 2016), Vols 1-5: Understanding Speech Processing in Humans and Machines
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectComParE
dc.subjectcomputational paralinguistics
dc.subjectNative Language
dc.subjectSincerity
dc.subjectFisher vector
dc.subjectPLS
dc.subjectELM
dc.subjectExtreme Learning-Machine
dc.subjectEmotion
dc.titleFusing Acoustic Feature Representations for Computational Paralinguistics Tasks
dc.typeConference Object

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
6081.PDF
Boyut:
237.61 KB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu
Çorlu Mühendislik Fakültesi Koleksiyonu