Show simple item record

AuthorKim, Bobaedc.contributor.author
Date of accession2019-08-07T15:24:45Zdc.date.accessioned
Available in OPARU since2019-08-07T15:24:45Zdc.date.available
Year of creation2018dc.date.created
Date of first publication2019-08-07dc.date.issued
AbstractSpeech emotion recognition has emerged in the area of speech signal research since it can have a signficant role in Artificial intelligent. In the area of speech emotion recognition, hand-engineered features are traditionally used as an input. However, it requires an additional step to extract features before the prediction and prior knowledge to select a feature set. For this reason, recent research is focusing on end-to-end speech emotion recognition to reduce the required efforts for the feature extraction and increase performance. Whereas this approach has been applied for prediction of categorical emotions, the study for prediction of continuous dimensional emotions is still rare. This paper presents a method for time-continuous prediction of emotions from speech in end-to-end manner. Proposed model comprises convolutional neural network (CNN) and Recurrent Neural Network with Long Short-Term Memory (RNN-LSTM). Hyperparameters of CNN are investigated to improve the performance of our model. After finding the optimal hyperparameters, the performance of the system with waveform and spectrogram as input is compared in terms of concordance correlation coefficient (CCC).dc.description.abstract
Languageendc.language.iso
PublisherUniversität Ulmdc.publisher
LicenseStandarddc.rights
Link to license texthttps://oparu.uni-ulm.de/xmlui/license_v3dc.rights.uri
KeywordTime-continuous emotion recognitiondc.subject
KeywordEnd-to-end modellingdc.subject
KeywordSpectrogramdc.subject
KeywordSpeech emotion recognitiondc.subject
Dewey Decimal GroupDDC 000 / Computer science, information & general worksdc.subject.ddc
Dewey Decimal GroupDDC 410 / Linguisticsdc.subject.ddc
LCSHEmotion recognitiondc.subject.lcsh
LCSHSpeech perceptiondc.subject.lcsh
LCSHMachine learningdc.subject.lcsh
LCSHArtificial intelligencedc.subject.lcsh
MeSHSpeech recognition softwaredc.subject.mesh
MeSHDeep learningdc.subject.mesh
TitleEnd-to-End time-continuous emotion recognition for spontaneous interactionsdc.title
Resource typeAbschlussarbeit (Master; Diplom)dc.type
Date of acceptance2018dcterms.dateAccepted
RefereeMinker, Wolfgangdc.contributor.referee
RefereeSchwenker, Friedhelmdc.contributor.referee
DOIhttp://dx.doi.org/10.18725/OPARU-17725dc.identifier.doi
PPN1670853144dc.identifier.ppn
URNhttp://nbn-resolving.de/urn:nbn:de:bsz:289-oparu-17782-9dc.identifier.urn
GNDEnde-zu-Ende-Prinzipdc.subject.gnd
GNDSonogrammdc.subject.gnd
GNDSchallaufzeichnungdc.subject.gnd
FacultyFakultät für Ingenieurwissenschaften, Informatik und Psychologieuulm.affiliationGeneral
InstitutionInstitut für Nachrichtentechnikuulm.affiliationSpecific
DCMI TypeTextuulm.typeDCMI
CategoryPublikationenuulm.category
University Bibliographyjauulm.unibibliographie


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record