Pengenalan Emosi Berdasarkan Suara Menggunakan Algoritma HMM
DOI:
https://doi.org/10.25126/jtiik.201743339Abstrak
Abstrak
Penelitian ini bertujuan mengenali emosi seseorang melalui ucapan menggunakan algoritma HMM. Sistem dibangun dapat mengenali 3 jenis emosi yaitu marah, bahagia dan netral. Fitur yang digunakan dalam sistem ini adalah pitch, energi dan formant. Database yang digunakan adalah suara dari rekaman film. Dari hasil obeservasi probabilitas emosi marah sebesar 0.196, bahagia 0.254 dan netral 0.045. Sistem memiliki tingkat akurasi rata-rata sebesar 86.66%. Rata waktu eksekusi sistem dalam mendeteksi dan mengklasifikasikan emosi sebesar 21.6ms.
Kata kunci: suara, emosi, HMM, klasifikasi
Abstract
This research aims to recognize human emotions through voice using HMM algorithm. The system can confirm three types of emotions: anger, happiness and neutrality. The features used in this system are pitch, energy and formant. From the results, the emotional probability of angry is 0.196, happy is 0.254 and neutral is 0.045. Base on testing result, the system has an average accuracy of 86.66% and average execution time of the system in detecting and classifying emotions of 21.6ms.
Keywords: voice, emotion, HMM, classification
Downloads
Biografi Penulis
-
Barlian Henryranu Prasetio, Laboratorium Sistem Komputer dan Robotika, Fakultas Ilmu Komputer, Universitas Brawijaya
Born in Banyuwangi October 24, 1982. Studied Electrical Engineering S1 at University Of Brawijaya and graduated in 2005, then went to the S2 level in 2008 and graduated in 2010. He worked in several state and private companies in East Java and eventually more interested in education, thus becoming a lecturer in Faculty of Computer Science, University of Brawijaya in January 2011.
He is interested in Embedded Systems and Robotics thus joined the Laboratory of Computer Systems and Robotics Faculty of Computer Science, University of Brawijaya.
Referensi
B. INGALE, D. S. CHAUDHARI, 2012, Speech Emotion Recognition Using Hidden Markov Model And Support Vector Machine. International Journal of Advanced Engineering Research and Studies (IJAERS), Vol. I, Issue 3, April-June, 316-318.
A. NOGUEIRAS, A. MORENO, A. BONAFONTE, J. B. MARINO, 2001, Speech emotion recognition using hidden Markov models, EUROSPEECH 2001 Scandinavia, 7th European Conference on Speech Communication and Technology, 2nd INTERSPEECH Event, Aalborg, Denmark, pp: 2679-2682
B. HEUFT, T. PORTELE, AND M. RAUTH, 1996, Emotions in time domain synthesis, inProc. of ICSLP, Philadelphia, pp. 1974–1977
B. SCHULLER, G. RIGOLL, M. LANG, 2003, Hidden Markov model-based Speech emotion recognition, Proceedings of the IEEE ICASSP Conference on Acoustics, Speech and Signal Processing, vol. 2, pp. 1-4.
D. VERVERIDIS, C. KOTROPOULOS, AND I. PITAS, 2004, Automatic emotional speech classification, in Proc. 2004 IEEE Int. Conf. Acoustics, Speech and Signal Processing, vol.1, pp. 593-596, Montreal, May.
F.YU, E.CHANG, Y.XU, H.SHUM, 2001, Emotion detection from speech to enrich multimedia content, Lecture Notes in Computer Science, Vol. 2195, 550-557.
N.H. FRIEDA, 1993, Moods, Emotion Episodes and Emotions, New York: Guilford Press, hal. 381-403.
T. L. PAO, W. Y. LIAO, Y. T. CHEN, J. H. YEH, 2008, Comparison of Several Classifiers for Emotion Recognition from Noisy Mandarin Speech, Third International Conference on Intelligent Information Hiding and Multimedia Signal Processing, Vol. 1, pp: 23-26
Y. PAN, PEIPEI SHEN AND LIPING SHEN, 2012, Speech Emotion Recognition Using Support Vector Machine, International Journal of Smart Home, Vol. 6, No. 2, April.
Unduhan
Diterbitkan
Terbitan
Bagian
Lisensi
Artikel ini berlisensi Creative Common Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)
Penulis yang menerbitkan di jurnal ini menyetujui ketentuan berikut:
- Penulis menyimpan hak cipta dan memberikan jurnal hak penerbitan pertama naskah secara simultan dengan lisensi di bawah Creative Common Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) yang mengizinkan orang lain untuk berbagi pekerjaan dengan sebuah pernyataan kepenulisan pekerjaan dan penerbitan awal di jurnal ini.
- Penulis bisa memasukkan ke dalam penyusunan kontraktual tambahan terpisah untuk distribusi non ekslusif versi kaya terbitan jurnal (contoh: mempostingnya ke repositori institusional atau menerbitkannya dalam sebuah buku), dengan pengakuan penerbitan awalnya di jurnal ini.
- Penulis diizinkan dan didorong untuk mem-posting karya mereka online (contoh: di repositori institusional atau di website mereka) sebelum dan selama proses penyerahan, karena dapat mengarahkan ke pertukaran produktif, seperti halnya sitiran yang lebih awal dan lebih hebat dari karya yang diterbitkan. (Lihat Efek Akses Terbuka).
