Personalized vocal learning system with adaptive verbal imagery

Bowen LIU, Siu Cheung KONG, Sing Kai LO, Ping LI

Research output: Chapter in Book/Report/Conference proceedingChapters


In this paper, we design an electronic vocal learning system with adaptive verbal imagery for vocal students. Our designed system can provide instructions on vocal technique for students using different kinds of verbal imagery. Our system can evaluate the performance of the student through analyzing the recorded voice data of the students. Based on the analyzed results of the students' performance and the types of verbal imagery applied, our system can automatically adjust the verbal imagery used in the following learning phases. The architecture of our system is discussed in details and a pilot study on potential users is conducted. Pilot study indicates that vocal students and learners expects more feedback in their learning process and our system is potentially beneficial for personalized voice education. Copyright © 2018 Global Chinese Society for Computers in Education. All rights reserved.
Original languageEnglish
Title of host publicationThe 22nd Global Chinese conference on computers in education: Conference proceedings
EditorsMorris JONG, Ju Ling SHIH, Chee Kit LOOI, Muxiong HUANG, Xionghui CHEN, Youru XIE, Xuebo ZHANG, Haiyun LI, Yi ZHANG, Daner SUN, Rita KUO, Seng Chee TAN, Wilfred LAU, Haoran XIE, Bo JIANG, Maggie WANG, Shikui TU
Place of PublicationGuangzhou
PublisherSouth China Normal University
Publication statusPublished - 2018


Liu, B., Kong, S. C., Lo, S. K., & Li, P. (2018). Personalized vocal learning system with adaptive verbal imagery. In M. Jong, J. L. Shih, C. K. Looi, M. Huang, X. Chen, Y. Xie, . . . S. Tu (Eds.), The 22nd Global Chinese Conference on Computers in Education: Conference proceedings (pp. 1450-1454). Guangzhou: South China Normal University.


  • Personalized learning
  • Verbal imagery
  • Voice teaching
  • PG student publication


Dive into the research topics of 'Personalized vocal learning system with adaptive verbal imagery'. Together they form a unique fingerprint.