Teaching Tips

SalukiSpeech: Integrating a New ASR Tool Into Students’ English Pronunciation Practice

---

Abstract

Recent research has shown that use of Automatic Speech Recognition (ASR)-based dictation for L2 pronunciation practice provides several benefits, including student improvement of segmental accuracy, noticing of probable errors at the word and sound level, and increased attention to segments with recurring errors. Further, the transcript can support greater learner autonomy by providing feedback and a sense of human intelligibility, which can be motivating for students. This paper introduces a new ASR-based tool that provides flexible, student-driven practice for students while also providing support for segmental learning. Focusing on providing communicative practice, the website offers learners the chance to practice English with guided, communicative learning activities while ASR provides implicit feedback in the form of a transcript. When students notice errors in the transcript, the system compares the intended word to the transcribed word to lead students to an appropriate segmental lesson. At the end of a practice session, students can email a summary report of their practice to their instructor. This paper introduces this new tool and discusses how it could be used for student pronunciation practice outside of class.

How to Cite: McCrocklin, S., Fettig, C, & Markus, S. (2022). Salukispeech: integrating a new ASR tool into students’ English pronunciation practice. In J. Levis & A. Guskaroska (eds.), Proceedings of the 12th Pronunciation in Second Language Learning and Teaching Conference, held June 2021 virtually at Brock University, St. Catharines, ON. https://doi.org/10.31274/psllt.13342