Integrated System Design for Broadcast Program Infringement Detection

Sukmawati Nur Endah (Diponegoro University)
Satriyo Adhy (Diponegoro University)
Sutikno Sutikno (Diponegoro University)

TELKOMNIKA (Telecommunication Computing Electronics and Control)
Vol 13, No 2: June 2015

Supervision of television and radio broadcast programs by the “Komisi Penyiaran Indonesia (KPI)” Central Java was still performed manually i.e. direct supervision by humans. It certainly had some weaknesses related to the human error such as tiredness and weary eyes. Therefore, we needed intelligent software that could automatically detect broadcast infringement. Currently, research in this area had not been studied. This research was to design an integrated system to detect broadcast infringement including data design, architecture design and main module interface design. Two main stages in this system are the Indonesian language speech recognition and detection of infringements of the broadcast program. With the method of Mel Frequency cepstral Coefficients (MFCC) and Hidden Markov Model (HMM) speech recognition application that used the 1050 sample data produces about 70% accuracy rate. This research would continue to implement the plan that had been created using speech recognition applications that had been built.