Abstract
We describe CALL-SLT, a speech-enabled Computer-Assisted Language Learning application where the central idea is to prompt the student with an abstract representation of what they are supposed to say, and then use a combination of grammar-based speech recognition and rule-based translation to rate their response. The system has been developed to the level of a mature prototype, freely deployed on the web, with versions for several languages. We present an overview of the core system architecture and the various types of content we have developed. Finally, we describe several evaluations, the last of which is a study carried out over about a week using 130 subjects recruited through the Amazon Mechanical Turk, in which CALL-SLT was contrasted against a control version where the speech recognition component was disabled. The improvement in student learning performance between the two groups was significant at p < 0.02.
Highlights
Introduction and backgroundPeople have been building Computer-Assisted Language Learning (CALL) applications for several decades, and more recently it has become popular to include speech recognition as one of the components
We briefly describe the various types of content we have developed for use in CALL-SLT
In an application like CALL-SLT, the student spends a large part of their time listening and repeating, which may well be helpful for them
Summary
People have been building Computer-Assisted Language Learning (CALL) applications for several decades, and more recently it has become popular to include speech recognition as one of the components. The system prompts the user in some version of the L1, indicating in an abstract or indirect fashion what they are supposed to say; the student speaks in the L2, and the system provides a response based on speech recognition and language processing. Irrespective of the modality used, the student, in order to respond correctly, must be able to pronounce the French words well enough to be understood by the speech recogniser; they need to CALL-SLT: A Spoken CALL System / 3 be able to construct a spoken French sentence whose meaning matches the content of the prompt. We present a number of evaluations (§4), where the central question addressed is whether the application is capable of helping students improve their language skills.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.