Accuracy Performance and Potentiality of Real-Time Avatar Lip Sync Animation in Different Languages
N. H. Loh1, S.S. Shaharuddin2
1N. H. Loh, Faculty of Applied and Creative Arts, Universiti Malaysia Sarawak, Kota Samarahan, Sarawak Malaysia.
2S.S. Shaharuddin, Faculty of Applied and Creative Arts, Universiti Malaysia Sarawak, Kota Samarahan, Sarawak Malaysia.
Manuscript received on 24 March 2019 | Revised Manuscript received on 03 April 2019 | Manuscript Published on 27 April 2019 | PP: 57-66 | Volume-7 Issue-6S2 April 2019 | Retrieval Number: F10100476S219/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: With the fast growth in computing power nowadays, the qualities of animation enable an extra layer of visually convincing realism. In lip sync animation, creation of realistic lip movement is arduous in getting the lip shape and position to synchronize with the speech sounds. To note, spending hours in manually generating every single lip movement can be a long and challenging task. Consequently, a comprehensive analysis on viseme based multiple phonemes in English, Bahasa Melayu and Mandarin was carried out, to develop an accurate and potential platform for real time talking avatar in multiple languages. The accuracy performance between human and avatar in real time were compared and evaluated. The findings revealed successful utilization of real time synchronization to drive the synthetic 3D avatars based on live speech input for multiple languages, with satisfied accurate lip motion result. This paper provides useful knowledge for multilingual solution which accurately predicts mouth movement on real human face, when a person is speaking and directs to lip sync process. It contributes to live performances and valuable in open-ended field with tons of potential, such as animation production industry, entertainment, gaming, digital marketing and media education.
Keywords: Avatar; Human Lip Shape; Lip Sync Animation; Real Time; Speech Recognition.
Scope of the Article: Real-Time Information Systems