Hierarchical Two-Level Modelling of Emotional States in Spoken Dialog Systems

Basit Öğe Kaydı
dc.authorid0000-0003-3424-652X
dc.authorid0000-0002-5583-0410
dc.authorid0000-0001-7947-5508
dc.authorwosidKarpov, Alexey A/A-8905-2012
dc.authorwosidFedotov, Dmitrii/AAE-1738-2019
dc.authorwosid????????, ??????/L-5818-2016
dc.contributor.authorVerkholyak, Oxana Vladimirovna
dc.contributor.authorFedotov, Dmitrii
dc.contributor.authorKaya, Heysem
dc.contributor.authorZhang, Yang
dc.contributor.authorKarpov, Alexey A.
dc.date.accessioned2022-05-11T14:15:55Z
dc.date.available2022-05-11T14:15:55Z
dc.date.issued2019
dc.departmentFakülteler, Çorlu Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü
dc.description44th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) -- MAY 12-17, 2019 -- Brighton, ENGLAND
dc.description.abstractEmotions occur in complex social interactions, and thus processing of isolated utterances may not be sufficient to grasp the nature of underlying emotional states. Dialog speech provides useful information about context that explains nuances of emotions and their transitions. Context can be defined on different levels; this paper proposes a hierarchical context modelling approach based on RNN-LSTM architecture, which models acoustical context on the frame level and partner's emotional context on the dialog level. The method is proved effective together with cross-corpus training setup and domain adaptation technique in a set of speaker independent cross-validation experiments on IEMOCAP corpus for three levels of activation and valence classification. As a result, the state-of-the-art on this corpus is advanced for both dimensions using only acoustic modality.
dc.description.sponsorshipInst Elect & Elect Engineers, Inst Elect & Elect Engineers Signal Proc Soc
dc.description.sponsorshipRussian Science FoundationRussian Science Foundation (RSF) [18-11-00145]; Huawei Innovation Research ProgramHuawei Technologies
dc.description.sponsorshipThe study is supported by the Russian Science Foundation (project No. 18-11-00145) and Huawei Innovation Research Program.
dc.identifier.endpage6704
dc.identifier.isbn978-1-4799-8131-1
dc.identifier.issn1520-6149
dc.identifier.scopus2-s2.0-85068970731
dc.identifier.scopusqualityN/A
dc.identifier.startpage6700
dc.identifier.urihttps://hdl.handle.net/20.500.11776/6119
dc.identifier.wosWOS:000482554006186
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.institutionauthorKaya, Heysem
dc.language.isoen
dc.publisherIEEE
dc.relation.ispartof2019 Ieee International Conference on Acoustics, Speech and Signal Processing (Icassp)
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectEmotion recognition
dc.subjectcross-corpus
dc.subjectcontext modelling
dc.subjectdialog systems
dc.subjectLSTM
dc.subjectCross-Corpus
dc.subjectRecognition
dc.titleHierarchical Two-Level Modelling of Emotional States in Spoken Dialog Systems
dc.typeConference Object

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
6119,.pdf
Boyut:
195.6 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