Metode Wavelet-MFCC dan Korelasi dalam Pengenalan Suara Digit

Voice is the sound emitted from living things. With the development of Automatic Speech Recognition (ASR) technology, voice can be used to make it easier for humans to do something. In the ASR extraction process the features have an important role in the recognition process. The feature extraction methods that are commonly applied to ASR are MFCC and Wavelet. Each of them has advantages and disadvantages. Therefore, this study will combine the wavelet feature extraction method and MFCC to maximize the existing advantages. The proposed method is called Wavelet-MFCC. Voice recognition method that does not use recommendations. Determination of system performance using the Word Recoginition Rate (WRR) method which is validated with the K-Fold Cross Validation with the number of folds is 5. The research dataset used is voice recording digits 0-9 in English. The results show that the digit speech recognition system that has been built gives the highest average value of 63% for digit 4 using wavelet daubechies DB3 and wavelet dyadic transform method. As for the comparison results of the wavelet decomposition method used, that the use of dyadic wavelet transformation is better than the wavelet package.

[1]  R.L.K. Venkateswarlu,et al.  The Performance Evaluation of Speech Recognition by Comparative Approach , 2012 .

[2]  Achmad Rizal.  Perbandingan Skema Dekomposisi Paket Wavelet untuk Pengenalan Sinyal EKG , 2015 .

[3]  Yoppy Sazaki,et al.  PENGENALAN SUARA MENGGUNAKAN MEL FREQUENCY CEPSTRAL COEFFICIENTS DAN SELF ORGANIZING MAPS , 2014 .

[4]  Risanuri Hidayat,et al.  Sistem Pengenal Tutur Bahasa Indonesia Berbasis Suku Kata Menggunakan MFCC, Wavelet Dan HMM , 2018 .

[5]  Sitti Amalia.  Pengenalan Digit 0 Sampai 9 Menggunakan Ekstraksi Ciri MFCC dan Jaringan Syaraf Tiruan Backpropagation , 2017 .

[6]  John H. L. Hansen,et al.  A Review on Speech Recognition Technique , 2010 .

[7]  Alex Acero,et al.  Spoken Language Processing: A Guide to Theory, Algorithm and System Development , 2001 .

[8]  Muhammad Rangga Aziz Nasution,et al.  Perbandingan Akurasi dan Waktu Proses Algoritma K-NN dan SVM dalam Analisis Sentimen Twitter , 2019, Jurnal Informatika.

[9]  M. Picheny,et al.  Comparison of Parametric Representation for Monosyllabic Word Recognition in Continuously Spoken Sentences , 2017 .

[10]  Omar Farooq,et al.  Phoneme recognition using wavelet based features , 2003, Inf. Sci..

[12]  Agus Harjoko,et al.  Pengenalan Ucapan Suku Kata Bahasa Lisan Menggunakan Ciri LPC, MFCC, dan JST , 2013 .

[13]  Abdurahim,et al.  Evaluation and design of wavelet packet cepstral coefficient (WPCC) for a noisy Indonesian vowels signal , 2019 .

[14]  Boko Susilo,et al.  Penerapan Speechrecognition pada Permainan Teka-Teki Silang Menggunakan Metode Hidden Markov Model (HMM) Berbasis Desktop , 2016 .

[15]  Nyoman Rizkha Emillia.  Penggunaan Hidden Markov Model Dan Genetic Algorithm Untuk Pemodelan Automatic Speech Recognition Pada Pengenalan Ucapan Bahasa Indonesia (Speech To Text) Usage Of Hidden Markov Models And Genetic Algorithm For Automatic Speech Recognition Modelling Of In , 2011 .