Pengenalan Ucapan Metoda MFCC-HMM Untuk Perintah Gerak Robot Mobil Penjejak Identifikasi Warna
Main Article Content
Keywords
Abstract
Dewasa ini, teknologi human machine cukup berkembang dan mendapatkan perhatian.. Dua bidang yang cukup berperan dalam perkembangan teknologi human machine adalah pemrosesan suara dan pemrosesan image. Penelitian ini mengimplementasikan pemrosesan suara dan image pada sistem robot mobil sehingga robot dapat mendengar, melihat, memberi respon dan diperintah berdasarkan ucapan. Sistem pengenalan ucapan menggunakan Mel Frequency Cepstrum Coefficient (MFCC) dan Hidden Markov Model (HMM). Robot mobil melakukan tracking objek berdasarkan empat jenis warna yaitu merah kuning, hijau dan biru. Pada penelitian ini segmentasi menggunakan metode multilevel color thresholding pada ruang warna HIS. Keluaran dari sistem robot mobil dihubungkan ke motor servo standar sebagai penggerak kamera dalam proses tracking objek. Keluaran sistem berupa gerakan horizontal kamera dan respon maju yang dilakukan robot mobil berdasarkan ucapan yang dikenali. Hasil pengujian untuk pengenalan ucapan sumber terlatih 83,33% dan untuk sumber tidak dilatih sebesar 80,25%. Sedangkan pengujian untuk objek tracking berdasarkan ucapan yang dikenali mencapai keberhasilan 100%. Oleh karena itu dapat disimpulkan bahwa robot dapat mentracking dan merespon objek.
Kata kunci : pengenalan ucapan, segmentasi, tracking objek
References
[2] Rabiner, “A Tutorial on Hidden Markov Model and Selected Aplications in Speech Recognition,” Proceedings of the IEEE, vol 77, No 2, 1989
[3] Tomi Aarnio, “Speech Recognition with Hidden Markov Models in Visual Communication,” Master of Science Thesis, University of Turki, 1999
[4] Ting Chee Ming,.” Malay Continous Speech Recognition using Continous Density Hidden Markov Model”, Thesis, Universiti Teknologi Malaysia, 2007.
[5] Mikael Nilson, marcus Ejnarson, “Speech recognition using Hidden Markov Model, Performance Evaluation in Noisy Environtment”, Theiss Blekinge institute of Technology, Sewen, 2002.
[6] Yao, Wang, J.Ostermann & Y.Q.Zhang. 2002. ”Video Processing and Communications”. New Jersey: Prentice Hall.
[7] Microsoft Corporation.2001. “Microsoft Paint Software”. New York: Microsoft Corporation.
[8] Hearn, Donald dan M. Pauline Baker. 1996. “Computer Graphics C Version 2nd Edition”. New York: Prentice Hall.
Article Sidebar
Article Details
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
The authors declare that:
1. This paper has not been published in the same form elsewhere.
2. It will not be submitted anywhere else for publication prior to acceptance/rejection by this Journal.
3. A copyright permission is obtained for materials published elsewhere and which require this permission for reproduction.
Fitrilina ., Jurusan Teknik Elektro Universitas Andalas
Jurusan Teknik ElektroUniversitas Andalas
Rahmadi Kurnia, Jurusan Teknik Elektro Universitas Andalas
Jurusan Teknik ElektroUniversitas Andalas
Siska Aulia, Jurusan Teknik Elektro Universitas Andalas
Jurusan Teknik ElektroUniversitas Andalas