Analisis rekognisi pengucap forensik sangat rutin diperlukan di Indonesia. Pengembangan sistem dari pendekatan fonetik-akustik menuju sistem rekognisi pengucap otomatis yang tidak bergantung teks menjadi sangat penting untuk dilakukan. Dalam pengujian dan pelatihan kinerjanya, sistem rekognisi pengucap otomatis memerlukan suatu basis data. Makalah ini membahas mengenai desain perekaman basis data suara ucap yang terdiri dari tiga skenario utama, yaitu data suara ucap, wawancara, dan percakapan natural. Media perekaman yang digunakan berupa satu buah mikrofon dan lima buah media perekaman portabel dengan kualitas yang beragam. Adapun bahasa yang digunakan pada saat perekaman adalah Bahasa Indonesia. Basis data suara ucap berbahasa Indonesia ini diharapkan dapat menjadi alat untuk pengembangan sistem rekognisi pengucap otomatis di Indonesia, khususnya untuk aplikasi forensik.
Eye blinking known as ocular artifact cause changes to the electric fields over the scalp and as a result, EEG recordings are often significantly distorted and theirinterpretation problematic. In this paper, an algorithm using second order blind identification with robust orthogonalization (SOBI-RO) is used to remove the ocular artifact in amotor imagery experiment.Simulation results shows that the ocular artifacts are significantly removed and the sources of the brain activity are clearly identified. The identification performance using signal to distortion ratio value about 68.88% is achieved.
Likelihood ratio calibration is a very important step when applying an automatic speaker recognition system to forensic applications. This paper presents the process and evaluation of a speaker recognition system developed with spoken Indonesian database. The system is developed using MFCC feature, GMM-UBM modeling, and Z normalization. System performances were evaluated based on male and female genders, and two scenarios i.e., natural conversation and interview. System evaluations were done using performance measures for both discrimination and calibration abilities. Results show that based on various indicators, the system behaves very well. This is shown by the best achievable EER values of 4.66%, and Cmc values of 0.04. Therefore, the developed automatic speaker recognition system is now ready to be used for forensic applications in Indonesia.
The purpose of this study was to determine the effect of providing fermented gliciridia fallen leaf and banana stem in complete feed with different level on crude fiber intake and digestibility, intake of digestible crude fiber, VFA concentration and blood glucose levels of kacang goat. This study used 4 male goats with age under one year, average body weight of 10.5 kg. The research used latin square design with 4 periods and 4 treatments, which consisted of P70S0, P40S30, P30S40, P0S70. The parameters observed were crude fiber intake and digestibility, intake of digestible crude fiber, VFA concentration and blood glucose levels. The results showed that the provision of complete gliciridia fallen leaf and banana stems with different level had no significant difference (P> 0.05) on crude fiber intake and digestibility, ingested digestive fiber consumption, blood glucose concentrations. However, feeding goats with a complete feed of gliciridia fallen leaf and banana stems with different levels had significantly increased (P <0.01) VFA concentration. Therefore, it can be concluded that providing goats with fermented complete feed of gliciridia fallen leaf and banana stem did not increase the value of crude fiber consumption and digestibility, consumption of undigested crude fiber and blood glucose levels but was able to increase VFA concentration
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.