A combined CNN architecture for speech emotion recognition

Simple item page
dc.contributor.advisorDongo Escalante, Irvin Franco Benito
dc.contributor.authorBegazo Huamani, Rolinson Jhiampier
dc.date.accessioned2024-12-06T15:54:36Z
dc.date.available2024-12-06T15:54:36Z
dc.date.issued2024
dc.description.abstractEmotion recognition through speech is a technique employed in various scenarios of Human–Computer Interaction (HCI). Existing approaches have achieved significant results; however, limitations persist, with the quantity and diversity of data being more notable when deep learning techniques are used. The lack of a standard in feature selection leads to continuous development and experimentation. Choosing and designing the appropriate network architecture constitutes another challenge. This study addresses the challenge of recognizing emotions in the human voice using deep learning techniques, proposing a comprehensive approach, and developing preprocessing and feature selection stages while constructing a dataset called EmoDSc as a result of combining several available databases. The synergy between spectral features and spectrogram images is investigated. Independently, the weighted accuracy obtained using only spectral features was 89%, while using only spectrogram images, the weighted accuracy reached 90%. These results, although surpassing previous research, highlight the strengths and limitations when operating in isolation. Based on this exploration, a neural network architecture composed of a CNN1D, a CNN2D, and an MLP that fuses spectral features and spectogram images is proposed. The model, supported by the unified dataset EmoDSc, demonstrates a remarkable accuracy of 96%.
dc.description.uriTrabajo académico
dc.formatapplication/html
dc.identifier.doihttps://doi.org/10.3390/s24175797
dc.identifier.urihttps://hdl.handle.net/20.500.12590/18477
dc.language.isoeng
dc.publisherUniversidad Católica San Pablo
dc.publisher.countryPE
dc.relation.urihttps://www.mdpi.com/1424-8220/24/17/5797
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.subjectSpeech emotion recognition
dc.subjectDeep learning
dc.subjectSpectral features
dc.subjectSpectrogram imaging
dc.subjectFeature fusion
dc.subjectConvolutional neural network
dc.subject.ocdehttp://purl.org/pe-repo/ocde/ford#2.00.00
dc.titleA combined CNN architecture for speech emotion recognition
dc.typeinfo:eu-repo/semantics/article
dc.type.versioninfo:eu-repo/semantics/publishedVersion
renati.advisor.dni46703945
renati.advisor.orcidhttps://orcid.org/0000-0003-4859-0428
renati.author.dni76774488
renati.discipline712096
renati.jurorSotomayor Polar, Manuel Gustavo
renati.jurorLudeña Choez, Jimmy Diestin
renati.levelhttps://purl.org/pe-repo/renati/level#tituloProfesional
renati.typehttps://purl.org/pe-repo/renati/type#trabajoAcademico
thesis.degree.disciplineIngeniería Electrónica y de Telecomunicaciones
thesis.degree.grantorUniversidad Católica San Pablo. Departamento de Ingeniería Electrónica y de Telecomunicaciones
thesis.degree.levelTítulo Profesional
thesis.degree.nameIngeniero Electrónico y de Telecomunicaciones
thesis.degree.programEscuela Profesional Ingeniería Electrónica y de Telecomunicaciones
Files
Original bundle
Now showing 1 - 5 of 5
Thumbnail Image
Name:
RESUMEN.pdf
Size:
159 KB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
BEGAZO_HUAMANI_ROL_COM.pdf
Size:
6.58 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
TURNITIN.pdf
Size:
9.08 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
ACTA.pdf
Size:
858.18 KB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
AUTORIZACION.pdf
Size:
710.05 KB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Artículos - Ingeniería Electrónica y de Telecomunicaciones