Please use this identifier to cite or link to this item:
http://studentrepo.iium.edu.my/handle/123456789/10984
Title: | Adaptive language processing unit for Malaysian sign language synthesizer | Authors: | Maarif, Haris Al Qodri | Supervisor: | Rini Akmeliawati, Ph.D Teddy Surya Gunawan, Ph.D |
Subject: | Sign language -- Computer-assisted instruction Natural language processing (Computer science) |
Year: | 2021 | Publisher: | Kuala Lumpur : Kulliyyah of Engineering, International Islamic University Malaysia, 2021 | Abstract in English: | Language Processing Unit (LPU) is a system built to process text-based data to comply with the rules of sign language grammar. This system was developed as an important part of the Sign Language Synthesizer system. Sign Language uses different grammatical rules from the spoken/verbal language, which only involves the important words that Hearing/Impaired Speech people can understand. It needs word classification by LPU to determine grammatically processed sentences for the sign language synthesizer. The existing language processing unit in SL synthesizers suffers time lagging and complexity problems, resulting in high processing time. The two features, i.e., the computational time and successful rate, become trade-offs which means the processing time becomes longer to achieve a higher success rate. To address this problem, this thesis proposes an adaptive Language Processing Unit (LPU) that allows processing the words from spoken words to Malaysian SL grammatical rule that results in relatively fast processing time and a good success rate. It involves n-grams, NLP, and Hidden Markov Models (HMM)/Bayesian Networks as the classifier to process the text-based input. As a result, the proposed LPU system has successfully provided an efficient (fast) processing time and a good success rate compared to LPU with other edit distances (Mahalanobis, Levenstein, and Soundex). The system has been tested on 130 text-input sentences with words ranging from 3 to 10 words. As a result, the proposed LPU could achieve around 1.449ms processing time with an average success rate of 84.49% for a maximum of ten-word sentences. | Call Number: | t HV 2474 M111A 2021 | Kullliyah: | Kulliyyah of Engineering | Programme: | Doctor of Philosophy (Engineering) | URI: | http://studentrepo.iium.edu.my/handle/123456789/10984 |
Appears in Collections: | KOE Thesis |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
t11100429161HarisAlQodriMaarif_24.pdf | 24 pages file | 399.7 kB | Adobe PDF | View/Open |
t11100429161HarisAlQodriMaarif_SEC.pdf Restricted Access | Full text secured file | 1.39 MB | Adobe PDF | View/Open Request a copy |
Google ScholarTM
Check
Items in this repository are protected by copyright, with all rights reserved, unless otherwise indicated. Please give due acknowledgement and credits to the original authors and IIUM where applicable. No items shall be used for commercialization purposes except with written consent from the author.