Computer-assisted language learning

• Main Author: Li, Yonger
• Other Authors: Chng Eng Siong
• Format: Final Year Project
• Language: English
• Published: 2014
• Subjects: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition; DRNTU::Engineering::Computer science and engineering::Information systems::Models and principles
• Online Access: http://hdl.handle.net/10356/61920
• Institution: Nanyang Technological University

In this project, common tonal and phonetic pronunciation errors of Mandarin Chinese made by second language learners are quantified. Tonal errors are found to be more frequent than phonetic errors. Among all the tonal errors, Tone 3 imposes the most challenge (51.9%) for the beginner learners. In terms of phonetic errors, speakers often mispronounced Hanyu Pinyin initial “zh” to “ch”. Thus, decision tree clustering model was developed to further characterize pronunciation error patterns in terms of their tonal and phonetic context. Additionally, statistical test was carried out to investigate how various demographic factors of speakers (i.e. gender, age, native language of speaker) affect the learning ability of the beginner learners. These finds are potentially useful in refining computer-assisted language learning software system in second language education.