Deep regression of social signals in Dyadic Scenarios

The purpose of this project is to design a general system for emotion recognition through social signals in dyadic using deep learning methods using raw data from audio, video and text transcriptions from publicly available database records. The automatic emotion recognition problem has increased th...

ver descrição completa

Detalhes bibliográficos
Autor: Vidal Lucero, Ítalo
Tipo de documento: dissertação
Data de publicação:2020
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositório:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglês
OAI Identifier:oai:upcommons.upc.edu:2117/336189
Acesso em linha:https://hdl.handle.net/2117/336189
Access Level:Acceso aberto
Palavra-chave:Neural networks (Computer science)
Machine learning
emotion recognition
recurrent neural networks
feature extraction
multi-modal database
dyadic scenario
Xarxes neuronals (Informàtica)
Aprenentatge automàtic
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
id ES_3daf6ea4dbfc3152d7350c3a0fdb8751
oai_identifier_str oai:upcommons.upc.edu:2117/336189
network_acronym_str ES
network_name_str España
repository_id_str
spelling Deep regression of social signals in Dyadic ScenariosVidal Lucero, ÍtaloNeural networks (Computer science)Machine learningemotion recognitionrecurrent neural networksfeature extractionmulti-modal databasedyadic scenarioXarxes neuronals (Informàtica)Aprenentatge automàticÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificialThe purpose of this project is to design a general system for emotion recognition through social signals in dyadic using deep learning methods using raw data from audio, video and text transcriptions from publicly available database records. The automatic emotion recognition problem has increased the attention in the scientific community considering the multi applications for emotion detection but also to design more accurate and complex empathic machines. During this project are proposed alternatives for utterance representation of multi-modal data generated from text, audio and video, in order to improve the state of the art system for emotion recognition based on deep learning networks. The proposed framework is based in IEMOCAP database but it has a general scope for any multi-modal database. The performance of this system outperforms the state of the art method and delivers an informative analysis concerning the utterance representation quality. Finally, the conclusions of this work are exposed along with potential future lines of work related to emotion recognition systems and emotion representations.Universitat Politècnica de CatalunyaEscalera Guerrero, SergioJacques Junior, JulioPalmero Cantariño, Cristina20202020-07-0120212021-01-29master thesishttp://purl.org/coar/resource_type/c_bdccNAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/masterThesisapplication/pdfhttps://hdl.handle.net/2117/336189reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/3361892026-05-27T15:37:01Z
dc.title.none.fl_str_mv Deep regression of social signals in Dyadic Scenarios
title Deep regression of social signals in Dyadic Scenarios
spellingShingle Deep regression of social signals in Dyadic Scenarios
Vidal Lucero, Ítalo
Neural networks (Computer science)
Machine learning
emotion recognition
recurrent neural networks
feature extraction
multi-modal database
dyadic scenario
Xarxes neuronals (Informàtica)
Aprenentatge automàtic
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
title_short Deep regression of social signals in Dyadic Scenarios
title_full Deep regression of social signals in Dyadic Scenarios
title_fullStr Deep regression of social signals in Dyadic Scenarios
title_full_unstemmed Deep regression of social signals in Dyadic Scenarios
title_sort Deep regression of social signals in Dyadic Scenarios
dc.creator.none.fl_str_mv Vidal Lucero, Ítalo
author Vidal Lucero, Ítalo
author_facet Vidal Lucero, Ítalo
author_role author
dc.contributor.none.fl_str_mv Escalera Guerrero, Sergio
Jacques Junior, Julio
Palmero Cantariño, Cristina
dc.subject.none.fl_str_mv Neural networks (Computer science)
Machine learning
emotion recognition
recurrent neural networks
feature extraction
multi-modal database
dyadic scenario
Xarxes neuronals (Informàtica)
Aprenentatge automàtic
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
topic Neural networks (Computer science)
Machine learning
emotion recognition
recurrent neural networks
feature extraction
multi-modal database
dyadic scenario
Xarxes neuronals (Informàtica)
Aprenentatge automàtic
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
description The purpose of this project is to design a general system for emotion recognition through social signals in dyadic using deep learning methods using raw data from audio, video and text transcriptions from publicly available database records. The automatic emotion recognition problem has increased the attention in the scientific community considering the multi applications for emotion detection but also to design more accurate and complex empathic machines. During this project are proposed alternatives for utterance representation of multi-modal data generated from text, audio and video, in order to improve the state of the art system for emotion recognition based on deep learning networks. The proposed framework is based in IEMOCAP database but it has a general scope for any multi-modal database. The performance of this system outperforms the state of the art method and delivers an informative analysis concerning the utterance representation quality. Finally, the conclusions of this work are exposed along with potential future lines of work related to emotion recognition systems and emotion representations.
publishDate 2020
dc.date.none.fl_str_mv 2020
2020-07-01
2021
2021-01-29
dc.type.none.fl_str_mv master thesis
http://purl.org/coar/resource_type/c_bdcc
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/336189
url https://hdl.handle.net/2117/336189
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universitat Politècnica de Catalunya
publisher.none.fl_str_mv Universitat Politècnica de Catalunya
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869406463064014848
score 15,300724

Registros relacionados