Javanese Gender Speech Recognition Based on Machine Learning Using Random Forest and Neural Network

Kristiawan Nugroho

Abstract


Speech is a means of communication between people throughout the world. At present research in the field of speech recognition continues to develop in producing a robust method in various research variants. However decreasing the word error rate or reducing noise is still a problem that is still being investigated until now. The purpose of this study is to find the right method with high accuracy to classify the gender voices of Javanese. This research used a human voice dataset of both men and women from the Javanese tribe which was recorded and then processed using a noise reduction preprocessing technique with the MFCC extraction feature method and then classified using 2 machine learning methods, namely Random Forest and Neural Network. Evaluation results indicate that the classification of Javanese accent speech accents results in an accuracy rate of 91.3 % using Random Forest and 92.2% using Neural Network.


Keywords


Speech, Random Forest, Neural Network, Accuration

Full Text:

PDF

References


L. Muda, M. Begam, dan I. Elamvazuthi, “Voice Recognition Algorithms using Mel Frequency Cepstral Coefficient (MFCC) and Dynamic Time Warping (DTW) Techniques,” vol. 2, no. 3, hlm. 6, 2010.

Shumaila Iqbal, T. Mehboob, dan M. Sikander Hayat Khiyal, “Voice Recognition using HMM with MFCC for Secure ATM.,” 2011.

M. Frikha dan A. Ben Hamida, “A Comparitive Survey of ANN and Hybrid HMM/ANN Architectures for Robust Speech Recognition,” AJIS, vol. 2, no. 1, hlm. 1–8, Agu 2012.

V. Mulik, V. Mane, dan I. Jamadar, “Hidden Markov Model Based Robust Speech Recognition,” International Journal of Innovative Research in Advanced Engineering, vol. 2, no. 2, hlm. 10, 2015.

Sreelakshmi, “Design of an Intelligent Speaker Recognition System using Mel Frequency Cepstrum Coefficients and Vector Quantization for Biometric Authentication,” 2015.

Z. S. Mada Sanjaya W.S, “Implementasi Pengenalan Pola Suara Menggunakan Mel-Frequency Cepstrum Coefficients (Mfcc) Dan Adaptive Neuro-Fuzzy Inferense System (Anfis) Sebagai Kontrol Lampu Otomatis,” 2014.

Q. Nada, C. Ridhuandi, P. Santoso, dan D. Apriyanto, “Speech Recognition dengan Hidden Markov Model untuk Pengenalan dan Pelafalan Huruf Hijaiyah,” vol. 5, no. 1, hlm. 8, 2019.

A. H.Mansour, G. Zen Alabdeen Salh, dan K. A. Mohammed, “Voice Recognition using Dynamic Time Warping and Mel-Frequency Cepstral Coefficients Algorithms,” IJCA, vol. 116, no. 2, hlm. 34–41, Apr 2015.

Leo Breiman, “Random Forests,” 2001.

Computer Science & Engineering &GZSCCET Bhatinda, Punjab, India, E. Goel, Er. Abhilasha, dan Computer Science & Engineering &GZSCCET Bhatinda, Punjab, India, “Random Forest: A Review,” IJARCSSE, vol. 7, no. 1, hlm. 251–257, Jan 2017.

B. Xu, J. Z. Huang, G. Williams, Q. Wang, dan Y. Ye, “Classifying Very High-Dimensional Data with Random Forests Built from Small Subspaces:,” International Journal of Data Warehousing and Mining, vol. 8, no. 2, hlm. 44–63, Apr 2012.

H. Kukreja, “An Introduction To Artificial Neural Network,” vol. 1, no. 5, hlm. 5, 2016.

O. S. Eluyode dan D. T. Akomolafe, “Comparative study of biological and artificial neural networks,” hlm. 11, 2013.

S. Kodati dan D. R. Vivekanandam, “Analysis of Heart Disease using in Data Mining Tools Orange and Weka,” hlm. 7, 2018.

P. K. Pattnaik, A. Swetapadma, dan J. Sarraf, Ed., Expert System Techniques in Biomedical Science Practice: IGI Global, 2018.




DOI: https://doi.org/10.24167/sisforma.v6i2.2402

Refbacks

  • There are currently no refbacks.


Bookmark and Share


SISFORMA: Journal of Information Systems | p-ISSN: 2355-8253 | e-ISSN: 2442-7888 | View My Stats

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.