Search

With competencies and the results of the engineering of natural language processing technology owned by BPPT since 1987, BPPT develops an English-Bahasa Indonesia speech-to-speech translation system (S2ST). In this paper, we propose an architecture of speech-to-speech translation system for Android-based mobile conversation using separate mobile devices for each language. This architecture applies three leading technologies, namely: WebSocket, REST, and JSON. The system utilizes a two-way communication protocol between two users and a simple voice activation detector that can detect a boundary of user's utterance.

To develop models of Natural Language Processing (NLP), such as speech recognition and speech synthesis, require the provision of a speech corpus that has been segmented and useful as training data. On the other hand, making a speech corpus costs a lot because it can include studio rent and payment of recorded speaker fees. Therefore, in this paper, we develop a tool for making speech corpus equipped with a function that guides the speaker to record their speech in sentences. This tool can be run independently on a personal computer so that we can do recording anytime and anywhere. To produce a better speech corpus, the recording results of this tool still require to be checked because they could potentially have a signal clip or low amplitudes.

Indonesia is the largest palm plantation that reaches 32 million tonnes palm oil production per year with 84 million tones Palm Oil Mill Effluent (POME) as liquid waste. POME contains many organic substances. The quality of POME for its utilization is generally measured in COD which has range 30000 -100.000 ppm. Microbial convertion for biogas especially for bio-H2 enrichment, the active sludge was pretreated physically to suppress methanogenesis microbes. H2 Biogas production was conducted at pH 5-6. Additional 10% phosphate buffer was done in the beginning only. The production of H2 biogas was influenced by hydrostatic pressure in closed batch system. Inoculumsmedium ratio also influenced the H2 biogas productivity, reached 0.7 ml/ml POME with more than 50% H2. Scaling up anaerobic in 2.5 L working volume bioreactor, H2 biogas productivity reached 0.86 ml/ml POME by 10% inoculums because of no hydrostatic pressure. In bio-reactor, H2-CO2 in H2 biogas was affected by the amount of active sludge. In the beginning of H2 biogas, H2 reached 80%. However, at subsequence process, fed batch, with retention time 2.5 day and 3 days H2 biogas production, the active sludge was accumulated and caused the decreasing H2, finally only 46% at the 3rd day. The consortium tended to produce more CO2 as the result of primary metabolite rather than H2. Raising inoculums to level 15% improved productivity only in the beginning but H2 content was getting less, only 59%. Additional feeding would cause more accumulation sludge and more decreasing H2 content to 31% on the 3rd day. Thus, the ratio of active sludge and substrate availability must be controlled to gain optimum H2. Limited substrate will cause the direction of bio-conversion more in CO2 rather than H2.