This research project was aimed to develop an intelligent Bengali handwriting education system to improve the literacy level in Bangladesh. Due to the socio-economical limitation, all of the population does not have the chance to go to school. Here, we developed a prototype of web-based (iPhone/smartphone or computer browser) intelligent handwriting education system for autonomous learning of Bengali characters that allows students to do practice their handwriting at anywhere at any time. As an intelligent tutor, the system can automatically check the handwriting errors, such as stroke production errors, stroke sequence errors, stroke relationship errors and immediately provide colourful error feedback to the students to correct themselves. Bengali is a multi-stroke input characters with extremely long cursive shape where it has stroke order variability and stroke direction variability. Due to this structural limitation, recognition speed is a crucial issue to apply traditional online handwriting recognition algorithm. In this work, we have adopted hierarchical recognition approach to improve the recognition speed that makes our system adaptable for web-based language learning. We applied writing speed free recognition methodology together with hierarchical recognition algorithm. It ensured the learning of all aged population, especially for children and older people. Finally, we conducted a survey in Bangladesh for the performance analysis of our proposed education system. The experimental results showed that our autonomous learning methodology helped to improve the average recognition accuracy by 4.1% (from 87.2% to 91.4%) with average Mean-Opinion-Score 4.1. It confirmed that the successful use of web-based Bengali handwriting education system can be very helpful to improve the literacy level in Bangladesh within a very short period.
A method for the segmentation and recognition of phonemes in spoken words uttered by unspecified speakers has been developed. Seven acoustic parameters are extracted every 10 ms from the outputs of the filter bank. The parameters are the frequencies of three spectral local peaks, the speech power, and three parameters expressing the gross pattern of the speech spectrum, which are obtained using a least-squares fit line to the spectrum. The segmentation into phonemes is carried out mainly using dynamic properties, which are the local minimum and maximum of the power and the three parameters mentioned above, in order to decrease errors due to inter-speaker variability and coarticulation. The recognition of phonemes is carried out using all the parameters. Some errors in the segmentation and recognition of phonemes can be corrected using phoneme connecting rules. In an experiment with 17 040 phoneme samples in 166 words uttered by 15 male speakers, the percentage of missed and inserted segments due to errors in segmentation were 4.3% and 10.1%, respectively, and the recognition accuracy was 82%, 60%, 56%, and 85% for vowels, semivowels, voiced consonants, and unvoiced consonants, respectively.
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.