SUST CSE Bangla Natural Language Processing Research Group consists of researchers, programmers, students & faculty who work on the critical areas of Bangla Natural Language Processing to develop tools and algorithms that will help computer and electronic devices to understand & process Bangla language better.
In this research a realistic Bangla OCR has been designed and developed from scratch, which can
actually recognize printed Bangla script with a very good accuracy.
Read More >
In this research a machine translation system is developed which can
translate English sentence(s) into Bangla. It uses the state of the art statistical machine
Read More >
This research is aimed on developing a natural sounding Bangla Text to Speech (TTS) synthesis system. The project is funded by the subproject ‘Development of
Read More >
The SUST Bangla Language Processing research team is working on Bangla Speech Processing (Bangla
Text to Speech – TTS or Speech synthesis
Read More >
56 volunteers of 18-26 age helped recording 11 bengali scripts consisting approximately 150 thousands words. We have recorded 250 Hours and labeled and tested them by 4 persons.
2 professional reciters (1 male and 1 female) gave their voice 25 Hours each. We used Sound recording Lab for Professional recording. These files were labeled and tested by 4 persons.
4 people work 2 months to translate English Sentences into Standard Bengali Sentences. We have converted the sentences as native as possible and avoided word-to-word meaning.
We have collected 200 hours of Youtube talk shows ,BBC news, audio books and volunteers wrote them. Based on those scripts we labeled the audio files and tested them by 4 persons.