Predicting depression and emotions in the cross-roads of cultures, para-linguistics, and non-linguistics

Basit Öğe Kaydı
dc.authorscopusid36241785000
dc.authorscopusid57195680712
dc.authorscopusid57209850146
dc.authorscopusid57195218979
dc.authorscopusid57209202409
dc.authorscopusid57210791723
dc.authorscopusid55412025900
dc.contributor.authorKaya, Heysem
dc.contributor.authorFedotov, D.
dc.contributor.authorDresvyanskiy, D.
dc.contributor.authorDoyran, M.
dc.contributor.authorMamontov, D.
dc.contributor.authorMarkitantov, M.
dc.contributor.authorSalah, Albert Ali
dc.date.accessioned2022-05-11T14:15:56Z
dc.date.available2022-05-11T14:15:56Z
dc.date.issued2019
dc.departmentFakülteler, Çorlu Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü
dc.descriptionACM SIGMM
dc.description9th International Audio/Visual Emotion Challenge and Workshop, AVEC 2019, held in conjunction with the ACM Multimedia 2019 -- 21 October 2019 -- -- 153196
dc.description.abstractCross-language, cross-cultural emotion recognition and accurate prediction of affective disorders are two of the major challenges in affective computing today. In this work, we compare several systems for Detecting Depression with AI Sub-challenge (DDS) and Cross-cultural Emotion Sub-challenge (CES) that are published as part of the Audio-Visual Emotion Challenge (AVEC) 2019. For both sub-challenges, we benefit from the baselines, while introducing our own features and regression models. For the DDS challenge, where ASR transcripts are provided by the organizers, we propose simple linguistic and word-duration features. These ASR transcriptbased features are shown to outperform the state of the art audio visual features for this task, reaching a test set Concordance Correlation Coefficient (CCC) performance of 0.344 in comparison to a challenge baseline of 0.120. Our results show that non-verbal parts of the signal are important for detection of depression, and combining this with linguistic information produces the best results. For CES, the proposed systems using unsupervised feature adaptation outperform the challenge baselines on emotional primitives, reaching test set CCC performances of 0.466 and 0.499 for arousal and valence, respectively. © 2019 Association for Computing Machinery.
dc.description.sponsorshipRussian Science Foundation, RSF: 18-11-00145
dc.description.sponsorshipThis study was partially conducted within the framework of the Russian Science Foundation project No. 18-11-00145.
dc.identifier.doi10.1145/3347320.3357691
dc.identifier.endpage35
dc.identifier.isbn978-1450369138
dc.identifier.scopus2-s2.0-85074945276
dc.identifier.startpage27
dc.identifier.urihttps://doi.org/10.1145/3347320.3357691
dc.identifier.urihttps://hdl.handle.net/20.500.11776/6125
dc.indekslendigikaynakScopus
dc.institutionauthorKaya, Heysem
dc.language.isoen
dc.publisherAssociation for Computing Machinery, Inc
dc.relation.ispartofAVEC 2019 - Proceedings of the 9th International Audio/Visual Emotion Challenge and Workshop, co-located with MM 2019
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectAffective Computing
dc.subjectCross-Cultural Emotion Recognition
dc.subjectDepression Severity Prediction
dc.subjectPTSD
dc.subjectAudio systems
dc.subjectForecasting
dc.subjectRegression analysis
dc.subjectSpeech recognition
dc.subjectAccurate prediction
dc.subjectAffective Computing
dc.subjectAudio-visual features
dc.subjectCorrelation coefficient
dc.subjectEmotion recognition
dc.subjectFeature adaptation
dc.subjectLinguistic information
dc.subjectPTSD
dc.subjectLinguistics
dc.titlePredicting depression and emotions in the cross-roads of cultures, para-linguistics, and non-linguistics
dc.typeConference Object

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
6125.pdf
Boyut:
1.9 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu
Çorlu Mühendislik Fakültesi Koleksiyonu