Speech emotion recognition using deep feedforward neural network
Speech emotion recognition (SER) is currently a research hotspot due to its challenging nature but bountiful future prospects. The objective of this research is to utilize Deep Neural Networks (DNNs) to recognize human speech emotion. First, the chosen speech feature Mel-frequency cepstral coefficie...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
IAES
2018
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/62495/ http://irep.iium.edu.my/62495/ http://irep.iium.edu.my/62495/ http://irep.iium.edu.my/62495/7/62495%20Speech%20emotion%20recognition%20SCOPUS.pdf http://irep.iium.edu.my/62495/13/62495_Speech%20emotion%20recognition%20using%20deep%20feedforward%20neural%20network_article.pdf |
| id |
iium-62495 |
|---|---|
| recordtype |
eprints |
| spelling |
iium-624952018-08-09T07:46:50Z http://irep.iium.edu.my/62495/ Speech emotion recognition using deep feedforward neural network Alghifari, Muhammad Fahreza Gunawan, Teddy Surya Kartiwi, Mira TK7885 Computer engineering Speech emotion recognition (SER) is currently a research hotspot due to its challenging nature but bountiful future prospects. The objective of this research is to utilize Deep Neural Networks (DNNs) to recognize human speech emotion. First, the chosen speech feature Mel-frequency cepstral coefficient (MFCC) were extracted from raw audio data. Second, the speech features extracted were fed into the DNN to train the network. The trained network was then tested onto a set of labelled emotion speech audio and the recognition rate was evaluated. Based on the accuracy rate the MFCC, number of neurons and layers are adjusted for optimization. Moreover, a custom-made database is introduced and validated using the network optimized. The optimum configuration for SER is 13 MFCC, 12 neurons and 2 layers for 3 emotions and 25 MFCC, 21 neurons and 4 layers for 4 emotions, achieving a total recognition rate of 96.3% for 3 emotions and 97.1% for 4 emotions. IAES 2018-05 Article PeerReviewed application/pdf en http://irep.iium.edu.my/62495/7/62495%20Speech%20emotion%20recognition%20SCOPUS.pdf application/pdf en http://irep.iium.edu.my/62495/13/62495_Speech%20emotion%20recognition%20using%20deep%20feedforward%20neural%20network_article.pdf Alghifari, Muhammad Fahreza and Gunawan, Teddy Surya and Kartiwi, Mira (2018) Speech emotion recognition using deep feedforward neural network. Indonesian Journal of Electrical Engineering and Computer Science, 10 (2). pp. 554-561. ISSN 2502-4752 http://www.iaescore.com/journals/index.php/IJEECS/article/view/11765/8301 10.11591/ijeecs.v10.i2.pp554-561 |
| repository_type |
Digital Repository |
| institution_category |
Local University |
| institution |
International Islamic University Malaysia |
| building |
IIUM Repository |
| collection |
Online Access |
| language |
English English |
| topic |
TK7885 Computer engineering |
| spellingShingle |
TK7885 Computer engineering Alghifari, Muhammad Fahreza Gunawan, Teddy Surya Kartiwi, Mira Speech emotion recognition using deep feedforward neural network |
| description |
Speech emotion recognition (SER) is currently a research hotspot due to its challenging nature but bountiful future prospects. The objective of this research is to utilize Deep Neural Networks (DNNs) to recognize human speech emotion. First, the chosen speech feature Mel-frequency cepstral coefficient (MFCC) were extracted from raw audio data. Second, the speech features extracted were fed into the DNN to train the network. The trained network was then tested onto a set of labelled emotion speech audio and the recognition rate was evaluated. Based on the accuracy rate the MFCC, number of neurons and layers are adjusted for optimization. Moreover, a custom-made database is introduced and validated using the network optimized. The optimum configuration for SER is 13 MFCC, 12 neurons and 2 layers for 3 emotions and 25 MFCC, 21 neurons and 4 layers for 4 emotions, achieving a total recognition rate of 96.3% for 3 emotions and 97.1% for 4 emotions. |
| format |
Article |
| author |
Alghifari, Muhammad Fahreza Gunawan, Teddy Surya Kartiwi, Mira |
| author_facet |
Alghifari, Muhammad Fahreza Gunawan, Teddy Surya Kartiwi, Mira |
| author_sort |
Alghifari, Muhammad Fahreza |
| title |
Speech emotion recognition using deep feedforward neural network |
| title_short |
Speech emotion recognition using deep feedforward neural network |
| title_full |
Speech emotion recognition using deep feedforward neural network |
| title_fullStr |
Speech emotion recognition using deep feedforward neural network |
| title_full_unstemmed |
Speech emotion recognition using deep feedforward neural network |
| title_sort |
speech emotion recognition using deep feedforward neural network |
| publisher |
IAES |
| publishDate |
2018 |
| url |
http://irep.iium.edu.my/62495/ http://irep.iium.edu.my/62495/ http://irep.iium.edu.my/62495/ http://irep.iium.edu.my/62495/7/62495%20Speech%20emotion%20recognition%20SCOPUS.pdf http://irep.iium.edu.my/62495/13/62495_Speech%20emotion%20recognition%20using%20deep%20feedforward%20neural%20network_article.pdf |
| first_indexed |
2023-09-18T21:28:34Z |
| last_indexed |
2023-09-18T21:28:34Z |
| _version_ |
1777412356494589952 |