Assessment of L2 Intelligibility: Comparing L1 Listeners and Automatic Speech Recognition

Autor/inn/en	Inceoglu, Solène; Chen, Wen-Hsin; Lim, Hyojung
Titel	Assessment of L2 Intelligibility: Comparing L1 Listeners and Automatic Speech Recognition
Quelle	In: ReCALL, 35 (2023) 1, S.89-104 (16 Seiten)Infoseite zur Zeitschrift PDF als Volltext Verfügbarkeit
Zusatzinformation	ORCID (Inceoglu, Solène) ORCID (Chen, Wen-Hsin) ORCID (Lim, Hyojung)
Sprache	englisch
Dokumenttyp	gedruckt; online; Zeitschriftenaufsatz
ISSN	0958-3440
DOI	10.1017/S0958344022000192
Schlagwörter	Second Language Learning; Intelligibility; Automation; Speech Communication; English (Second Language); Foreign Countries; Taiwan + Suchen Sie Ihr Suchwort? Zweitsprachenerwerb; English as second language; English; Second Language; Englisch als Zweitsprache; Ausland
Abstract	An increasing number of studies are exploring the benefits of automatic speech recognition (ASR)-based dictation programs for second language (L2) pronunciation learning (e.g. Chen, Inceoglu & Lim, 2020; Liakin, Cardoso & Liakina, 2015; McCrocklin, 2019), but how ASR recognizes accented speech and the nature of the feedback it provides to language learners is still largely under-researched. The current study explores whether the intelligibility of L2 speakers differs when assessed by native (L1) listeners versus ASR technology, and reports on the types of intelligibility issues encountered by the two groups. Twelve L1 listeners of English transcribed 48 isolated words targeting the /[near-close front unrounded vowel]-i/ and /[near-open front unrounded vowel]-[open-mid front unrounded vowel]/ contrasts and 24 short sentences that four Taiwanese intermediate learners of English had produced using Google's ASR dictation system. Overall, the results revealed lower intelligibility scores for the word task (ASR: 40.81%, L1 listeners: 38.62%) than the sentence task (ASR: 75.52%, L1 listeners: 83.88%), and highlighted strong similarities in the error types -- and their proportions -- identified by ASR and the L1 listeners. However, despite similar recognition scores, correlations indicated that the ASR recognition of the L2 speakers' oral productions mirrored the L1 listeners' judgments of intelligibility in the word and sentence tasks for only one speaker, with significant positive correlations for one additional speaker in each task. This suggests that the extent to which ASR approaches L1 listeners at recognizing accented speech may depend on individual speakers and the type of oral speech. (As Provided).
Anmerkungen	Cambridge University Press. 100 Brook Hill Drive, West Nyack, NY 10994. Tel: 800-872-7423; Tel: 845-353-7500; Fax: 845-353-4141; e-mail: subscriptions_newyork@cambridge.org; Web site: https://www.cambridge.org/core/what-we-publish/journals
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2024/1/01