THE JOURNAL OF ASIA TEFL Vol. 17, No. 3, Fall 2020, 824-840 http://dx.doi.org/10.18823/asiatefl.2020.17.3.5.824 824 The Journal of Asia TEFL http://journal.asiatefl.org/ e-ISSN 2466-1511 © 2004 AsiaTEFL.org. All rights reserved. ASR for EFL Pronunciation Practice: Segmental Development and Learners’ Beliefs Solène Inceoglu Australian National University, Australia Hyojung Lim Kwangwoon University, Korea Wen-Hsin Chen National Taipei University of Technology, Taiwan The current study explored the usefulness of mobile-based automatic speech recognition (ASR) pronunciation practice by investigating a) its effects on the production of four English vowels, and b) learners’ perception of ASR as a learning tool. A total of 19 Korean university students produced 28 minimal pair sentences containing the English vowel contrasts /i/-/ɪ/ and /ɛ/-/æ/ (e.g., I said beat, I said bit) at pretest and posttest, and completed six sessions of ASR practice outside of class that involved voice-typing a short text, minimal pairs in sentences, and decontextualized minimal pairs. Results of acoustic analysis of F1 and F2 formant frequencies showed a meaningful improvement in frontness for the vowel /i/, but no changes for the other vowels. Overall, the majority of the participants perceived ASR as useful for pronunciation practice, but some showed skepticism and frustration regarding the current state of the technology. Further discussed are the problems and limitations that EFL learners experienced during the ASR training. Keywords: automatic speech recognition (ASR), EFL pronunciation, learners' beliefs, vowel production, pronunciation training Introduction The pedagogical benefits of automatic speech recognition (ASR), also referred to as speech-to-text, voice-recognition, or dictation, have been highlighted in second language (L2) teaching and learning research (Cucchiarini & Strik, 2018; Levis & Suvorov, 2012). The use of ASR appears to contribute to reading development in children (Mostow, Huang, & Junker, 2008) and ASR might be used to address common errors in L2 Dutch morphology and syntax (Cucchiarini, Van Doremalen, & Strik, 2008). In the domain of pragmatics, Chiu, Liou, and Yeh (2007) reported that ASR-based oral activities in a simulated real-life conversation helped Taiwanese freshman students learn English speech acts. Undeniably, the strongest contribution that ASR technology makes is in the area of oral skills and pronunciation. Among the affordances for language teaching and learning that ASR provides, Golonka et al. (2014, p. 73) listed that ASR can: