Klasifikasi Usia Berdasarkan Suara Dengan Ekstraksi Ciri Mel Frequency Cepstral Coefficients Menggunakan Support Vector Machine

Mufi Oktaviani(1*), Taufik Edy Sutanto(2), M Mahmudi(3),

(1) Universitas Islan Negeri Syarif Hidayatullah Jakarta, Indonesia
(2) Universitas Islan Negeri Syarif Hidayatullah Jakarta, Indonesia
(3) Universitas Islan Negeri Syarif Hidayatullah Jakarta, Indonesia
(*) Corresponding Author

Abstract


Each individual has a different and unique voice, this can potentially be used to determine a person's age. Classification can be done through a feature extraction process using Mel Frequency Cepstral Coefficients (MFCC). Then the extraction results can be used as features in machine learning models such as Support Vector Machines. Data was collected by recording 100 voices of informants, then the feature extraction process was carried out using MFCC, and then classified using Support Vector Machine. Age categories set are children (0-14), teenagers (15-40) and elderly (40+). Then the data samples were duplicated for variety using noise, shift and dynamic change methods so that 6000 sound samples were obtained. Our model can result in an accuracy of 75,8% and the recall obtained in the children category is a percentage of 80%. Researchers hope that these results can be a reference for human age recognition application systems for voice-based classification.

Full Text:

PDF

References


Mirza Ardiana, Titon Dutono, and Tri Budi Santoso, “Identifikasi Jenis Kelamin Secara Real Time Berdasarkan Suara Pada Raspberry Pi,” J. Politek. Caltex Riau, vol. 8, no. 1, (2022), pp. 158–167.

M.Tri Satria Jaya, Diyah Puspitaningrum, and Boko Susilo, “Penerapan Speech Recognition Pada Permainan Teka-Teki Silang Menggunakan Metode Hidden Markov Model (HMM) Berbasis Desktop,” J. Rekursif, vol. 4, no. 1, (2016), pp. 119–129.

A. Abdillah Alwi, P. Pandu Adikara, and Indriati, “Pengenalan Jenis Kelamin dan Rentang Umur berdasarkan Suara menggunakan Metode Backpropagation Neural Network,” J. Pengemb. Teknol. Inf. Dan Ilmu Komput., vol. 4, no. 7, (2020), pp. 2083–2093.

N. Kumar Goel, M. Sarma, T. Singh Kushwah, D. Kumar Agrawal, Z. Iqbal, and S. Chauhan, “Extracting speaker’s gender, accent, age and emotional state from speech,” Interspeech,(2018), pp. 2384–2385, doi: 10.1088/1742-6596/1410/1/012073.

Heriyanto, S. Hartati, and A. Eko Putra, “Ekstraksi Ciri Mel Frequency Cepstral Coefficient ( MFCC ) dan Rerata Coefficient Untuk Pengecekan Bacaan Al- Qur ’an,” Telematika, vol. 15, (2018), pp. 99–108.

A. Abdulsatar, V. Davydov, V. Yushkova, A. Glinushkin, and V. Rud, “Age and gender recognition from speech signals,” J. Phys. Conf. Ser., vol. 1, (2019), doi: 10.1088/1742-6596/1410/1/012073.

D. Katerenchuk, “Age Group Classification with Speech and Metadata Multimodality Fusion,” Aclanthology.org, (2017), pp. 188–193.

Teguh Puji Laksono, Speech To Text Untuk Bahasa Indonesia, (2018).

D. Putra and A. Resmawan, “Verifikasi Biometrika Suara Menggunakan Metode MFCC Dan DTW,” LONTAR Komput., vol. 2, no. 1, (2011), pp. 8–21.

Totok Chamidy, “Metode Mel Frequency Cepstral Coeffisients (MFCC) Pada klasifikasi Hidden Markov Model (HMM) Untuk Kata Arabic pada Penutur Indonesia,” J. MATICS, vol. 8, no. 1, (2016), pp. 36–39, , doi: 10.18860/mat.v8i1.3482.

Angga Setiawan, Achmad Hidayatno, and R. Rizal Isnanto, “Aplikasi Pengenalan Ucapan dengan Ekstraksi Mel-Frequency Cepstrum Coefficients (MFCC) Melalui Jaringan Syaraf Tiruan (JST) Learning Vector Quantization (LVQ) untuk Mengoperasikan Kursor Komputer,” TRANSMISI, vol. 13, no. 3, (2011), pp. 80–86,.

Torkis Nasution, “Metoda Mel Frequency Cepstrum Coefficients (MFCC) untuk Mengenali Ucapan pada Bahasa Indonesia,” J. Sains Dan Teknol. Inf., vol. 1, no. 1, (2012), pp. 22–31, doi: https://doi.org/10.33372/stn.v1i1.309.

P. Singh, R. Srivastava, K. P. S. Rana, and V. Kumar, “A multimodal hierarchical approach to speech emotion recognition from audio and text,” Knowl.-Based Syst., vol. 229,(2021).[Online]. Available:https://www.sciencedirect.com/science/article/abs/pii/S0950705121005785

A. Rahman Fauzi, Simulasi Control Smart Home Berbasis Mel Frequency Cepstral Coefficient Menggunakan Metode Support Vector Machine (SVM). UIN Sunan Ampel, (2020).[Online].Available: http://digilib.uinsa.ac.id/43041/2/Arif%20Rahman%20Fauzi_H06216003.pdf

Ryan Rifkin and Aldebaro Klautau, “In Defense of One-Vs-All Classification,” J. Mach. Learn. Res., vol. 5, (2004), pp. 101–141.

Renaldy Irfan, Analisis Perbandingan Algoritma K-nearest Neighbor Dengan Algoritma Support Vector Machine Pada Pengklasifikasia. (2012). [Online]. Available: https://repository.uinjkt.ac.id/dspace/bitstream/123456789/55999/1/RENALDY%20IRFAN-FST.pdf

I. Syarif, A. Prugel-Bennett, and G. Wills, “SVM Parameter Optimization Using Grid Search and Genetic Algorithm to Improve Classification Performance,” TELKOMNIKA, vol. 14, no. 4, (2016), pp. 1502-1509. doi : 10.12928/TELKOMNIKA.v14i4.3956.




DOI: https://doi.org/10.30645/kesatria.v4i4.240

DOI (PDF): https://doi.org/10.30645/kesatria.v4i4.240.g238

Refbacks

  • There are currently no refbacks.


Published Papers Indexed/Abstracted By: