MODEL KLASIFIKASI EMOSI BERDASARKAN SUARA DENGAN METODE MULTILAYER PERCEPTRON
Human-computer interaction technology has developed, for example, speech recognition. One of the uses of speech recognition is to recognize human emotions. Computers can recognize and classify human emotions based on sound. There have been many studies related to various method of feature extraction...
Saved in:
| Main Author: | |
|---|---|
| Format: | Book |
| Published: |
2021-01-28.
|
| Subjects: | |
| Online Access: | Link Metadata |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
MARC
| LEADER | 00000 am a22000003u 4500 | ||
|---|---|---|---|
| 001 | repoupnvj_9307 | ||
| 042 | |a dc | ||
| 100 | 1 | 0 | |a Deni Ardiansyah, . |e author |
| 245 | 0 | 0 | |a MODEL KLASIFIKASI EMOSI BERDASARKAN SUARA DENGAN METODE MULTILAYER PERCEPTRON |
| 260 | |c 2021-01-28. | ||
| 500 | |a http://repository.upnvj.ac.id/9307/1/ABSTRAK.pdf | ||
| 500 | |a http://repository.upnvj.ac.id/9307/2/AWAL.pdf | ||
| 500 | |a http://repository.upnvj.ac.id/9307/3/BAB%201.pdf | ||
| 500 | |a http://repository.upnvj.ac.id/9307/4/BAB%202.pdf | ||
| 500 | |a http://repository.upnvj.ac.id/9307/5/BAB%203.pdf | ||
| 500 | |a http://repository.upnvj.ac.id/9307/6/BAB%204.pdf | ||
| 500 | |a http://repository.upnvj.ac.id/9307/7/BAB%205.pdf | ||
| 500 | |a http://repository.upnvj.ac.id/9307/8/DAFTAR%20PUSTAKA.pdf | ||
| 500 | |a http://repository.upnvj.ac.id/9307/11/RIWAYAT%20HIDUP.pdf | ||
| 500 | |a http://repository.upnvj.ac.id/9307/13/LAMPIRAN.pdf | ||
| 500 | |a http://repository.upnvj.ac.id/9307/12/ARTIKEL_KI.pdf | ||
| 520 | |a Human-computer interaction technology has developed, for example, speech recognition. One of the uses of speech recognition is to recognize human emotions. Computers can recognize and classify human emotions based on sound. There have been many studies related to various method of feature extraction and classification but the results are still not close to perfect. The feature extraction method uses the Mel Frequency Ceptral Coefficient (MFCC). The data used is secondary data sourced from the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS). The system model will be able to recognize 8 types of emotions, namely neutral, calm, happy, sad, angry, scared, disgusted and surprised. The results of the model obtained accuracy for neutral emotions by 98%, calm emotions by 97%, happy emotions by 94%, sad emotions by 97%, angry emotions by 97%, fearful emotions by 94%, disgust emotions by 97% and shocking emotions. by 96%. So that the results of the average accuracy of the models that have been made are 96%. | ||
| 546 | |a id | ||
| 546 | |a id | ||
| 546 | |a id | ||
| 546 | |a id | ||
| 546 | |a id | ||
| 546 | |a id | ||
| 546 | |a id | ||
| 546 | |a id | ||
| 546 | |a id | ||
| 546 | |a id | ||
| 546 | |a id | ||
| 690 | |a QA75 Electronic computers. Computer science | ||
| 655 | 7 | |a Thesis |2 local | |
| 655 | 7 | |a NonPeerReviewed |2 local | |
| 787 | 0 | |n http://repository.upnvj.ac.id/9307/ | |
| 787 | 0 | |n https://repository.upnvj.ac.id | |
| 856 | 4 | 1 | |u http://repository.upnvj.ac.id/9307/ |z Link Metadata |