Iowa State University - Thesis & Dissertation
The effects of ASR-based practice on learners’ perception of L2 sounds
Abstract
dc:description.abstractDespite the growing body of research demonstrating the effectiveness of automatic speech recognition (ASR) tools, such as Google Translate (GT), in supporting second language pronunciation learning, most existing studies focus on learners’ production gains in self-directed settings. No research has been found investigating whether ASR-mediated practice influences learners’ perception skills. Grounded in the close relationship between perception and production, this study examines whether integrating GT ASR into pronunciation homework enhances learners’ perception abilities for two English vowel contrasts (/i-ɪ/ and /æ-ɛ/). Using a pretest–training–posttest design, this study compared an experimental group (EG) and a control group (CG) that received identical classroom instruction in four sessions across two weeks. The in-class training included explicit pronunciation instruction, corrective feedback, and minimal-pair practice. The two groups differed only in their homework practice: the EG used the ASR function of GT to check the intelligibility of their homework pronunciation, while the CG completed equivalent practice without ASR support. It was hypothesized that ASR-mediated feedback would raise learners’ awareness of pronunciation errors and facilitate improvements in their perception of L2 vowels by promoting additional listening to model speech provided by GT. However, the results revealed no significant difference in perceptual gains between the two groups. Both groups showed significant improvement from pretest to posttest, with similar effect sizes. One possible explanation is that the relatively short training duration was insufficient for the added benefits of ASR-mediated homework practice to emerge. Another explanation might be that the training was delivered by an experienced pronunciation instructor, which may have made the effects of using ASR less pronounced.
Degree
thesis:*- Name thesis:degree_name
- Master of Arts
- Level thesis:degree_level
- thesis
- Discipline thesis:degree_discipline
- Linguistics
- Grantor
- Iowa State University - Thesis & Dissertation
- Year dc:date.issued
- 2026
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Nguyen, Quang, Xuan
- Advisor dc:contributor.advisor
-
- Sonsaat-Hegelheimer, Sinem
Subjects
dc:subject × 1Rights
- Language dc:language.iso
- en_US
Identifiers
dc:identifier.*- Repository record dc:identifier.uri
- https://dr.lib.iastate.edu/handle/20.500.12876/106726
- OAI identifier oai:identifier
- oai:dr.lib.iastate.edu:20.500.12876/106726