PEMODELAN PROBABILISTIK NEURAL NETWORK UNTUK KONVERSI SUARA GITAR KE CORD

Arviani Rizki, Agus Buono

Abstract


Almost allmusic genreuse guitaras its instrument.Toproducea harmonicguitarvoice needs guitar chords mastery. However, only few peopleareable todistinguish guitar chords. This paper is addressed to develop a computational model to convert guitar voice into appropriate cord. In this research, we use Mel Frequency Cepstrum Coefficient (MFCC) as feature extraction because thistechniqueis oftenusedfor voice processing and good enough in presenting thecharacteristics ofasignal voice. Probabilistic Neural Network (PNN) is implemented to classify the feature into one out of 24 classes of cord. We record 345 for each cord (totally we have 8640 recording data with WAV format). Experimenst are conducted for some number of cepstral coefficients (13, 26, 39 and 52), with 100 millisecond as time frame and 40% overlapping between successive frame. According to the experiment, the maximum accuracy is 94.31% for 52 number of cepstral coefficients.


Keywords


Chord-identification, Mel Frequency Cepstral Coefficients (MFCC), Probabilistic Neural Network, Speaker Recognition.

References


Buono A. (2009). Representasi Nilai HOS dan Model MFCC Sebagai Ekstraksi Ciri Pada Sistem Identifikasi Pembicara di Lingkungan Ber-Noise Menggunakan HMM.[Disertasi]. Depok: Program Pascasarjana, Universitas Indonesia.

Fransiswa RR. (2010). Pengembangan Model Probabilistic Neural Network (PNN) pada pengenalan kisaran usia dan jenis kelamin berbasis suara.[Skripsi]. Jurusan Ilmu Komputer, Fakultas Matematika dan Ilmu Pengetahuan Alam, Institut Pertanian Bogor.

Ganchev T. (2009). Speaker recognition [disertasi]. Patras (GR): University of Patras.

M. Nilsson & M. Ejnarsson. (2002). Speech Recognition using Hidden Markov Model : Performance Evaluation in Noisy Environment. Master Thesis, Departement of Telecommunications and Signal Processing, Blekinge Institute of Technology.

Wisnudisastra E, Buono A. (2010). Pengenalan Chord pada Alat Musik Gitar Menggunakan CodeBook dengan Teknik Ekstraksi Ciri MFCC.Jurnal Ilmiah Ilmu Komputer, Vol 14 No. 1, Mei 2010 : 16 – 21.


Refbacks

  • There are currently no refbacks.