An ASR-based Reading Tutor for Practicing Reading Skills in the First Grade: Improving Performance through Threshold Adjustment

Yu Bai, Ferdy Hubers, Catia Cucchiarini, Helmer Strik

Automatic Speech Recognition (ASR) technology can potentially be employed to provide intensive practice and feedback to young children learning to read. So far there has been limited research on the use of ASR in the early stages of learning to read when children are still developing decoding skills. For this purpose we developed an ASR-based system equipped with logging capabilities that can evaluate decoding skills in Dutch first graders reading aloud and provide them with detailed, individualized feedback. In a previous study we found that ASR-based feedback led to improved reading accuracy and speed and that useful information could be obtained from the log-files, which in turn could be employed to improve practice and feedback.In the present paper we conducted thorough analyses of the performance of this ASR- based system by comparing it to human annotations of the same read aloud 11849 words from 38 pupils so as to gain more detailed information on the nature of the ASR errors. We present the results of these experiments and discuss how they can be employed to improve the system and to contribute to better and more personalized ASR-based reading instruction.

doi: 10.21437/IberSPEECH.2021-3

Bai, Y, Hubers, F, Cucchiarini, C, Strik, H (2021) An ASR-based Reading Tutor for Practicing Reading Skills in the First Grade: Improving Performance through Threshold Adjustment. Proc. IberSPEECH 2021, 11-15, doi: 10.21437/IberSPEECH.2021-3.