Pronounce Perfectly or Communicate Productively: Modifying Speech Recognition Technology for EFL students

ID: 48692 Type: Best Practices Session
  1. Todd Cooper, National Institute of Technology, Fukui College, Japan
  2. Akira Tsukada and Tomoki Matsunaga, National Institute of Technology, Toyama College, Japan

Wednesday, June 29 2:45 PM-3:05 PM Location: Grand Ballroom AB

Presider: Kurt Ackermann, Hokusei Gakuen University Junior College, Japan

Abstract: Speech recognition [SR] technology is revolutionizing our interactions with computers and smartphones. It also has the potential to change how we teach foreign language, by offering the possibility to provide a “virtual set of ears” to each student, effectively creating a one-to-one learning environment. Unfortunately, SR doesn’t always work so well. And when attempting to use with EFL learners, these problems multiply. In this study, we will detail our attempts to use SR software in the EFL classroom for the purposes of interview and speaking assessment, and how we plan to modify the SR engine for use by EFL students at a poly-technical college in Japan. We are not focusing on the acquisition of perfect pronunciation, as is required by most SR engines. We are focusing on productive communication, which creates the need to customize existing software.


Conference attendees are able to comment on papers, view the full text and slides, and attend live presentations. If you are an attendee, please login to get full access.