Penerapan Hidden Markov Model (HMM) dan Mel-Frequency Cesptral Coefficients (MFCC) pada E-Learning Bahasa Madura untuk Anak Usia Dini

Abstract

Bahasa Madura is a regional language used in Madura island. This language has many variations of pronunciation and dialect that makes it not easy to learn, even by the local people especially children. There hasn’t been any interesting learning media to learn Bahasa Madura so far. In fact, a fun learning activity is needed to help children to enhance their ability in pronouncing animals’ names, numbers, fruits and things in Bahasa Madura. Thus, it’s considered important to create Bahasa Madura e-learning by implementing the recognition of voice patterns in order to make it easier for the children to learn Bahasa Madura which has several variations of pronunciation only for one single object. This Bahasa Madura e-learning application for young learners is used to introduce Bahasa Madura vocabularies by recognizing the voice pattern recordings which have been processed through MFCC technique as the extracted voice features and HMM as the learning techniques. The implementation of MFCC and HMM as the learning tool to introduce the pronunciation of regional language vocabularies especially Bahasa Madura has never been done before. Therefore, this research is expected to help the young learners to be able to pronounce Bahasa Madura vocabularies properly.  In this study, a number of young learners’ voices were recorded and were set as the trial data. Only the proper voice data that were used—voice data that were considered to be pronounced correctly. The trial method was done through one-single model and multi-model. After doing several simultaneous trials, the result showed the accuracy level. The average accuracy level for one-single model system was 73% (with the highest accuracy reached 75%) and the average accuracy level for multi-model system was 80% (with the highest accuracy reached 81%).Bahasa Madura adalah Bahasa Daerah yang digunakan di Pulau Madura. Bahasa ini memiliki banyak variasi pengucapan dan dialek. Hal ini menyebabkan Bahasa Madura tidak mudah untuk dipelajari bahkan oleh masyarakat Madura khususnya anak-anak. Saat ini belum ada media pembelajaran Bahasa Madura yang menarik untuk mempelajari Bahasa Madura. Padahal melalui pembelajaran yang menyenangkan diharapkan dapat membantu anak untuk memperoleh kemampuan melatih penerapan pengucapan nama binatang, angka, buah dan benda dalam Bahasa Madura. Karena itulah perlu dibuat e-learning Bahasa Madura dengan menerapkan pengenalan pola suara sehingga dapat membantu anak mengenal Bahasa Madura yang memiliki variasi pengucapan untuk objek yang sama. Aplikasi e-learning Bahasa Madura untuk anak usia dini digunakan untuk mengenalkan nama objek dalam Bahasa Madura melalui pengenalan pola suara yang diucapkan dibuat dengan menggunakan teknik Mel-Frequency Cesptral Coefficients (MFCC) sebagai ekstrak fitur suara dan Hidden Markov Model (HMM) sebagai teknik pembelajarannya. Penerapan MFCC dan HMM untuk pengenalan pengucapan Bahasa Daerah khususnya Bahasa Madura belum pernah ada sebelumnya, sehingga dengan adanya penelitian ini diharapkan dapat membantu anak usia dini mengenal pengucapan kata Bahasa Madura dengan benar. Pada penelitian ini, sejumlah anak direkam suaranya untuk dijadikan sebagai data training. Data suara yang digunakan adalah data suara yang pengucapan dianggap benar. Skenario percobaan dilakukan dengan menggunakan satu model dan multi model. Setelah dilakukan serangkaian percobaan, hasil penelitian menunjukkan yaitu rata-rata akurasi untuk pengujian sistem dengan satu model yaitu 73% dengan akurasi tertinggi 75% dan rata-rata akurasi untuk pengujian sistem dengan multi model yaitu 80% dengan akurasi tertinggi 81%. AbstractBahasa Madura is a regional language used in Madura island. This language has many variations of pronunciation and dialect that makes it not easy to learn, even by the local people especially children. There hasn’t been any interesting learning media to learn Bahasa Madura so far. In fact, a fun learning activity is needed to help children to enhance their ability in pronouncing animals’ names, numbers, fruits and things in Bahasa Madura. Thus, it’s considered important to create Bahasa Madura e-learning by implementing the recognition of voice patterns in order to make it easier for the children to learn Bahasa Madura which has several variations of pronunciation only for one single object. This Bahasa Madura e-learning application for young learners is used to introduce Bahasa Madura vocabularies by recognizing the voice pattern recordings which have been processed through MFCC technique as the extracted voice features and HMM as the learning techniques. The implementation of MFCC and HMM as the learning tool to introduce the pronunciation of regional language vocabularies especially Bahasa Madura has never been done before. Therefore, this research is expected to help the young learners to be able to pronounce Bahasa Madura vocabularies properly.  In this study, a number of young learners’ voices were recorded and were set as the trial data. Only the proper voice data that were used—voice data that were considered to be pronounced correctly. The trial method was done through one-single model and multi-model. After doing several simultaneous trials, the result showed the accuracy level. The average accuracy level for one-single model system was 73% (with the highest accuracy reached 75%) and the average accuracy level for multi-model system was 80% (with the highest accuracy reached 81%).