Please use this identifier to cite or link to this item: https://dspace.univ-ouargla.dz/jspui/handle/123456789/28063
Full metadata record
DC FieldValueLanguage
dc.contributor.authorDalal, Djeridi-
dc.contributor.authorRayhana, Kedidi-
dc.date.accessioned2022-04-17T09:26:05Z-
dc.date.available2022-04-17T09:26:05Z-
dc.date.issued2020-09-
dc.identifier.urihttp://dspace.univ-ouargla.dz/jspui/handle/123456789/28063-
dc.descriptionUNIVERSITY OF KASDI MERBAH OUARGLA FACULTY of new Information Technologies and Communication DEPARTMENT of computer science and Information Technologyen_US
dc.description.abstractRecognizing emotions has become an area of great interest to researchers in the past few years. Emotion recognition is a multidisciplinary area, among which is the recognition of emotions from speech. Recognizing speech emotion is a significant endeavor in human speech processing and developing human-computer interaction. This work presents the performance of machine learning approaches for the recognition of emotions from an Arabic speech signal. Initially, we used the Lebanese audio database Arabic-Natural-Audio-Dataset (ANAD), which contains 384 records with 505 happy, 137 surprises, and 741 angry units. Next, we use the OpenSMILE toolkit to extract the necessary speech features with two methods, Low-Level Descriptors (LLDs) with 988 features, and Mel-frequency cepstral coefficient (MFCC) with 39 features. Also, we applied features selection on LLDs and MFCC using Learner Based Feature Selection. We suggested Rough set theory for select features in order to improve results. Then, for classifying the emotions into different classes, Multilayer Perceptron (MLP), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Logistic Regression (LR) are employed. Results showed that MLP outperformed other models when applied on LLDs and MFCC features with accuracy 87%, 83% respectively.en_US
dc.language.isoenen_US
dc.publisherUNIVERSITY OF KASDI MERBAH OUARGLAen_US
dc.subjectArabic speech signalen_US
dc.subjectspeech emotion recognitionen_US
dc.subject(LLDs)en_US
dc.subjectMachine learningen_US
dc.titleEmotion recognition in Arabic speech signalen_US
dc.typeThesisen_US
Appears in Collections:Département d'informatique et technologie de l'information - Master

Files in This Item:
File Description SizeFormat 
.Djeridi-.Kedidi.pdfThe rest of the thesis is organized as follows: in the last part of the general introduction, we explain the related works with the study, including Arabic and external studies. Chapter I describe the necessary information related to the Arabic speech signal. Chapter II presents the Materials and methods used for the dataset and in writing code. The Implementation of the code ,results analysis and evaluation showed in Chapter III. We concluded the thesis with the general conclusion that explains the essential steps that we discussed in this work and what can be applied in the future.1,83 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.