Abstract. This paper discusses the usage of the short-term energy contour of speech smoothed by a fuzzy-based method to automatically segment it into syllabic units. Two new additional procedures, local normalization and postprocessing, are proposed to adapt to the Indonesian language. Testing to 220 Indonesian utterances showed that the local normalization significantly improved the performance of the fuzzy-based smoothing. In the postprocessing procedure, splitting and assimilation work in different ways. The splitting of missed short syllables sharply reduced deletion, but slightly increased insertion. On the other hand, the assimilation of a single consonant segment into an expected previous or next segment slightly reduced insertion, but increased deletion. The use of splitting gave a higher accuracy than the assimilation and combined splittingassimilation procedures, since in many cases the assimilation keeps the unexpected insertions and overmerges the expected segments.Keywords: assimilation, fuzzy-based smoothing; Indonesian language; local normalization; short-term energy contour; splitting; syllable segmentation. IntroductionInformation on syllabic units can be used to improve the performance of flat start-based automatic speech recognition (ASR) [1]- [11]. In 2010, Janakiraman et al. [11] reported that incorporating information on syllable boundaries into English ASR reduced both computational complexity and word error rate (WER) significantly compared to flat start ASR. The WER can be reduced from 13% to 4.4% and from 36% to 21.2% for TIMIT and NTIMIT databases respectively.Every language has unique characteristics. For example, English and Indonesian have different syllable patterns. A study of telephone conversations and switchboard corpus by has shown that English has 80% monosyllabic words and 85% of them are simple structures (V, VC, CV, CVC)

No abstract

<p class="0abstract">Visible Light Communication (VLC) as one of wireless technology must be able to offer a good capability as mobile communication system. The signal will be faded when the distance and angle of LED to photo-detector become higher at a certain distance. Other problem at VLC system is light interference noise which is caused by flicker effect from other light sources such as incandescent, fluorescent, DC-lamp (i.e. flashlight) and the sunlight. Each of lights have specific carried signal characteristics and it can influences the VLC system. In this paper we offer design of mobile VLC system based on analog domain. We use Automatic Gain Controller (AGC) circuit using commercially available IC and it will be placed at analog front-end receiver side. AGC can self-adjust its gain according to the input signal amplitude.  We also design analog filter to eliminate all interferences noise spectrum which is existed under 50 KHz. We design both circuits, analog filter and AGC in VLC receiver system with low-cost. The test data are obtained through the simulation and achieved good results in ideal condition.</p>

Abstract-To date, the photodiode still the first choice component is used in optical communication, especially for visible light communication (VLC) system. It has advantages of speed, energy consumption, and sensitivity, compared to other devices (e.g. image sensor). There are many practical implementations of high-speed VLC which uses photodiode. Commercially available photodiode typically have specific characteristics, so that it needs some consideration to be used as optimal receiver devices in VLC system. In this paper, analysis of received power characteristics of the photodiode in indoor lineof-sight (LoS) channel of VLC system is discussed. MATLAB® simulation is used as approach model (student version). The experiments are done by changing several parameters such as the semi-angle half power of the transmitter, distance from the transmitter to receiver, room size, field-of-view (FOV), lens index and optical filter gain. From the results, it can be known that distance, room size, FOV and LED power factor to have linear characteristic against the received power of commercial photodiode. Also in LoS channel model, the gain of optical filter and lens index plays an important role in defining the characteristics of received power.

AbstrakBelajar membaca Al-Qur’an menggunakan alat bantu aplikasi sangat diperlukan dalam mempermudah dan memahami bacaan Al-Qur’an. Pengecekan bacaan Al-Qur’an salah satu metode dengan MFCC untuk pengenalan suara cukup baik dalam speech recognition.Metode tersebut telah lama diperkenalkan oleh Davis dan Mermelstein sekitar tahun 1980. MFCC merupakan metode ekstraksi ciri untuk mendapatkan cepstral coefficient dan frame sehingga dapat digunakan untuk pemrosesan pengenalan suara agar lebih baik dalam ketepatan. Tahapan MFCC mulai dari pre-emphasis, frame blocking, windowing, Fast Fourier Transform (FFT), Mel Frequency Wrapping (MFW), Discrete Cosine Transoform (DCT) dan cepstral liftreing. Hasil pengecekan bacaan Al-Qur’an diujikan dalam sebelas surat mulai dari surat Al-Fatihah, Al-Baqarah, Al-Imran, Al-Hadid, Al-Ashr, Ar-rahman, Al-Alaq, Al-Kautsar, Al-Ikhlas, Al-Falaq dan An-Nas menghasilkan akurasi sebesar rata-rata 51,8%. Kata Kunci : Suara, Bacaan,  MFCC, Kesesuaian, Ekstraksi Ciri, Referensi, Bobot, Dominan.