학술논문
Using Google Voice Typing to Automatically Assess Pronunciation
Document Type
Speeches/Meeting Papers
Reports - Research
Reports - Research
Author
Johnson, Carol (ORCID 0000-0001-6859-6566 ); Cardoso, Walcir (ORCID 0000-0001-6376-185X ); Zuercher, Beau; Brannen, Kathleen; Springer, Suzanne
Source
Subject
Language
English
Abstract
This study examined the use of a popular Automatic Speech Recognition (ASR), Google Voice Typing (GVT), to automatically assess English as second language pronunciation. It aimed to answer the following question: What is the relationship between GVT-rated scores and human-rated scores? To answer this question, we compared audio recordings of 56 oral placement tests, rated by both human raters and GVT. Our results indicate that GVT scores strongly correlated with human-rater scores, indicating that this non-customizable ASR technology could be leveraged to increase the test usefulness of language placement tests. [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.]