Evaluating Automatic Speech Recognition for L2 Pronunciation Feedback: A Focus on Google Translate [Konferenzbericht] Paper presented at the EUROCALL 2022 Conference (30th, Reykjavik, Iceland, Aug 17-19, 2022).

Autor/inn/en	John, Paul; Cardoso, Walcir; Johnson, Carol
Titel	Evaluating Automatic Speech Recognition for L2 Pronunciation Feedback: A Focus on Google Translate [Konferenzbericht] Paper presented at the EUROCALL 2022 Conference (30th, Reykjavik, Iceland, Aug 17-19, 2022).
Quelle	(2022), (7 Seiten) PDF als Volltext kostenfreie Datei Verfügbarkeit
Zusatzinformation	ORCID (John, Paul) ORCID (Cardoso, Walcir) ORCID (Johnson, Carol)
Sprache	englisch
Dokumenttyp	gedruckt; online; Monographie
Schlagwörter	Second Language Learning; Second Language Instruction; Audio Equipment; Accuracy; French Canadians; Foreign Countries; Pronunciation; Translation; Computer Software; Error Analysis (Language); English (Second Language); Pronunciation Instruction; Feedback (Response); Gender Bias; Gender Differences; Females; Teaching Methods; Computational Linguistics; Sentences; Canada + Suchen Sie Ihr Suchwort? Zweitsprachenerwerb; Fremdsprachenunterricht; Audio-CD; Frankokanadier; Ausland; Aussprache; Error analysis; Language; Fehleranalyse; English as second language; English; Second Language; Englisch als Zweitsprache; Ausspracheübung; Geschlechterstereotyp; Geschlechterkonflikt; Weibliches Geschlecht; Teaching method; Lehrmethode; Unterrichtsmethode; Linguistics; Computerlinguistik; Sentence analysis; Satzanalyse; Kanada
Abstract	This study examines the L2 pronunciation feedback provided by the Automatic Speech Recognition (ASR) functionality in Google Translate (GT). We focus on three Quebec Francophone (QF) errors in English: th-substitution, h-deletion, and h-epenthesis. Four hundred and eighty male and female QF recordings of sentences with correctly and incorrectly pronounced final items (e.g. "I don't know who to thank versus tank") were played into GT. Errors were equally divided between mispronunciations leading to real word ("thank" [right arrow] "tank") and nonword output ("thief" [right arrow] "tief"). As anticipated, we found greater transcription accuracy for correct pronunciations and, among incorrect pronunciations, for real words versus nonwords. Overall, our findings suggest ASR can be highly effective for pronunciation feedback. We also examined transcriptions for gender bias, since ASR systems are often trained on corpora with more male voices, but our concerns proved unfounded: surprisingly, higher transcription accuracy was found for female recordings. [For the complete volume, "Intelligent CALL, Granular Systems and Learner Data: Short Papers from EUROCALL 2022 (30th, Reykjavik, Iceland, August 17-19, 2022)," see ED624779.] (As Provided).
Anmerkungen	Research-publishing.net. La Grange des Noyes, 25110 Voillans, France. e-mail: info@research-publishing.net; Web site: http://research-publishing.net
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2024/1/01