ASR for EFL Pronunciation Practice: Segmental Development and Learners’ Beliefs

Abstract

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/-/ae/ (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.

Automatic speech recognition and text-to-speech technologies for L2 pronunciation improvement

“…Levis and Suvorov (2013, p. 319) state that many studies indicate that "software that includes ASR is a huge plus to language learners in terms of practice, motivation, and the feeling that they are actually communicating in the language rather than simply repeating predigested words and sentences". This is congruent with the results of other studies based on the perception of both students and teachers that yield positive reactions towards ASR (CHEN, 2011;INCEOGLU;LIM;CHEN, 2020). In addition, this positive reaction might be connected to the fact that learners comprehend the importance of pronunciation for successful communication, being keen to use technological resources to improve it (ROGERSON-REVELL, 2021).…”

“…ASR can be defined as "an independent, machine-based process of decoding and transcribing oral speech" (LEVIS; SUVOROV, 2013, p. 316). By building a string of words from an acoustic signal, it can be applied to dictation (a single specific speaker's monologue transcription) tools, or humancomputer interaction (JURAFSKY; MARTIN, 2020), such as Intelligent Personal Assistant (IPA) embedded to smart devices (e.g., smartphones and smart speakers) (INCEOGLU;LIM;CHEN, 2020;MOUSSALLI;CARDOSO, 2020). This technology started to be developed by the late 1940s and early 1950s.…”

“…Furthermore, ASR can be applied in varied ways to facilitate the learning process, inside and outside the classroom (KIM, 2006;CHEN, 2011;LEVIS;SUVOROV, 2013;GOLONKA et al, 2014;ASHWELL;ELAM, 2017;LIAKIN;CARDOSO;LIAKINA, 2017;MROZ, 2018;DIZON, 2020;DIZON;TANG, 2020;INCEOGLU;LIM;CHEN, 2020;MCCROCKLIN;EDALATISHAMS, 2020;ROGERSON-REVELL, 2021). To put it concisely, based on the aforementioned studies, ASR tools can contribute to pronunciation improvement by: • allowing the development of L2 learners' autonomy, offering an opportunity for learners to work on their pronunciation individually, at a self-selected pace; • encouraging learners to produce more output in a low-anxiety environment, talking to a tireless listener (the algorithm); • helping learners to improve not only their pronunciation but also their oral communication skills, speaking fluency, and accuracy;…”

Assessment of L2 intelligibility: Comparing L1 listeners and automatic speech recognition

“…Recent studies have started to examine how ASR tools can enhance the learning of segmentals in instructional settings (Chen et al, 2020;García, Nickolai & Jones, 2020;Guskaroska, 2019;Inceoglu et al, 2020;Liakin et al, 2015;McCrocklin, 2019). Generalizations are currently difficult to make due to the small number of studies and the variety of L1s/L2s investigated.…”

How Well Can Asr Technology Understand Foreign-Accented Speech?

“…Speech technology such as pronunciation apps, websites, computer programs, and dictation tools offers interesting possibilities for this end. From the growing body of research on the field of L2 pronunciation and speech technology (ASHWELL; ELAM, 2017;INCEOGLU;LIM;CHEN, 2020;LIAKINA, 2017;EDALATISHAMS, 2020;MROZ, 2018), it is clear that the topic has called researchers' interest, becoming an area of its own -computer-assisted pronunciation teaching (CAPT).…”