Indonesian Alphabet Speech Recognition for Early Literacy using Convolutional Neural Network Approach
Games are considered capable of being used as a learning medium that can help teachers to teach children how to pronounce the Indonesian alphabet in early literacy, we try to build one aspect of the game in this study. The approach we use is a speech recognition approach that uses the convolutional...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universitas Udayana
2020-02-01
|
| Series: | Journal of Electrical, Electronics and Informatics |
| Online Access: | https://ojs.unud.ac.id/index.php/JEEI/article/view/60184 |
| _version_ | 1818478465761935360 |
|---|---|
| author | Duman Care Khrisne Theresia Hendrawati |
| author_facet | Duman Care Khrisne Theresia Hendrawati |
| author_sort | Duman Care Khrisne |
| collection | DOAJ |
| description | Games are considered capable of being used as a learning medium that can help teachers to teach children how to pronounce the Indonesian alphabet in early literacy, we try to build one aspect of the game in this study. The approach we use is a speech recognition approach that uses the convolutional neural network method. The results of this study indicate that CNN can recognize speech, with input data is in the form of sound. We use the MFCC feature vector sound feature to make a 3-dimensional matrix of input sound into CNN input. We also use the Sequential CNN architecture made from a simple 10 layer neural network, which produces a model with a small size, approximately only about 6 MB, with high accuracy (84%) and an F-Measure of 0.91. |
| first_indexed | 2024-12-10T09:48:40Z |
| format | Article |
| id | doaj.art-7196f7b41a2440e9a1b47a5ad77e5493 |
| institution | Directory Open Access Journal |
| issn | 2549-8304 2622-0393 |
| language | English |
| last_indexed | 2024-12-10T09:48:40Z |
| publishDate | 2020-02-01 |
| publisher | Universitas Udayana |
| record_format | Article |
| series | Journal of Electrical, Electronics and Informatics |
| spelling | doaj.art-7196f7b41a2440e9a1b47a5ad77e54932022-12-22T01:53:44ZengUniversitas UdayanaJournal of Electrical, Electronics and Informatics2549-83042622-03932020-02-0141343710.24843/JEEI.2020.v04.i01.p0660184Indonesian Alphabet Speech Recognition for Early Literacy using Convolutional Neural Network ApproachDuman Care Khrisne0Theresia Hendrawati1Udayana UniversitySTMIK STIKOM IndonesiaGames are considered capable of being used as a learning medium that can help teachers to teach children how to pronounce the Indonesian alphabet in early literacy, we try to build one aspect of the game in this study. The approach we use is a speech recognition approach that uses the convolutional neural network method. The results of this study indicate that CNN can recognize speech, with input data is in the form of sound. We use the MFCC feature vector sound feature to make a 3-dimensional matrix of input sound into CNN input. We also use the Sequential CNN architecture made from a simple 10 layer neural network, which produces a model with a small size, approximately only about 6 MB, with high accuracy (84%) and an F-Measure of 0.91.https://ojs.unud.ac.id/index.php/JEEI/article/view/60184 |
| spellingShingle | Duman Care Khrisne Theresia Hendrawati Indonesian Alphabet Speech Recognition for Early Literacy using Convolutional Neural Network Approach Journal of Electrical, Electronics and Informatics |
| title | Indonesian Alphabet Speech Recognition for Early Literacy using Convolutional Neural Network Approach |
| title_full | Indonesian Alphabet Speech Recognition for Early Literacy using Convolutional Neural Network Approach |
| title_fullStr | Indonesian Alphabet Speech Recognition for Early Literacy using Convolutional Neural Network Approach |
| title_full_unstemmed | Indonesian Alphabet Speech Recognition for Early Literacy using Convolutional Neural Network Approach |
| title_short | Indonesian Alphabet Speech Recognition for Early Literacy using Convolutional Neural Network Approach |
| title_sort | indonesian alphabet speech recognition for early literacy using convolutional neural network approach |
| url | https://ojs.unud.ac.id/index.php/JEEI/article/view/60184 |
| work_keys_str_mv | AT dumancarekhrisne indonesianalphabetspeechrecognitionforearlyliteracyusingconvolutionalneuralnetworkapproach AT theresiahendrawati indonesianalphabetspeechrecognitionforearlyliteracyusingconvolutionalneuralnetworkapproach |