Speech and Language Technology in Education (SLaTE 2013)

Grenoble, France
August 30-September 1, 2013

Spoken Grammar Practice in an ASR-based CALL System

Bart Penning de Vries, Stephen Bodnar, Catia Cucchiarini, Helmer Strik, Roeland van Hout

Centre for Language and Speech Technology, Radboud University Nijmegen, the Netherlands

In this paper we present a computer assisted language learning (CALL) system that is developed to practice grammar in spoken language. To enable this, the system uses Automatic Speech Recognition (ASR) to process the L2 learner's responses. We investigate the possibility of providing corrective feedback (CF) on learner errors, and compare that with self-monitored language learning through output practice. In this paper we present the comparison of the two conditions 1) one group of learners received oral practice and CF on spoken performance, and 2) the other group received oral practice and no CF on spoken performance. We found that our system is successful for L2 speaking practice. The main finding is that both groups show learning after treatment. Between the groups, we did not find a learning difference, but the groups' sessions proceeded differently. Additionally we found that the CF group was more positive about the system than the NO CF group.

Index Terms: second language acquisition, corrective feedback, speech recognition, CALL

Full Paper

Bibliographic reference.  Vries, Bart Penning de / Bodnar, Stephen / Cucchiarini, Catia / Strik, Helmer / Hout, Roeland van (2013): "Spoken grammar practice in an ASR-based CALL system", In SLaTE-2013, 60-65.