# Speech to text for Indonesian homophone phrase with Mel Frequency Cepstral Coefficient
> Bustamin A.

URL kanonis: https://discover.unhas.ac.id/publications/speech-to-text-for-indonesian-homophone-phrase-with-mel-frequency-cepstral-coeff
Jurnal / Konferensi: Proceedings Cyberneticscom 2016 International Conference on Computational Intelligence and Cybernetics
Tahun terbit: 2017
DOI: https://doi.org/10.1109/CyberneticsCom.2016.7892562
Citations: 4

## Authors
- Bustamin A.

## Abstract
In this study, speech to text system for homophone phrases in Indonesian was designed using an extraction method which featured Mel Frequency Cepstral Coefficient (MFCC). Feature extraction results were classified by comparing the two classifiers of Backpropagation Neural Network (BPNN) and K-Nearest Neigbour (KNN). The input data used were the recordings of each of 3 male and female respondents. The recording process was conducted for 5 seconds at a sampling frequency of 16 kHz and at channel mono. Classification results with test data to BPNN showed accuracy rates of 96.67% and 90% respectively for male and female respondents. Moreover, the level of accuracy obtained on KNN amounted to 83.33% for males and 73.33% for females.

## Keywords
- Mel-frequency cepstrum
- Speech recognition
- Feature extraction
- Computer science
- Phrase
- Homophone
- Artificial intelligence
- Pattern recognition (psychology)
- Cepstrum
- Artificial neural network
- Philosophy
- Linguistics

---
Sumber: Discover Unhas — RIMS Universitas Hasanuddin.
Saat mengutip, gunakan DOI bila tersedia atau URL kanonis di atas.