2021 Fiscal Year Annual Research Report
A cross-institutional study into speech recognition for language learners, analyzing usage patterns
| Project/Area Number |
18K00825
|
|---|
| Research Institution | Kanazawa University |
|---|
Principal Investigator |
Gary Ross 金沢大学, 薬学系, 准教授 (10708142)
|
|---|
| Project Period (FY) |
2018-04-01 – 2022-03-31
|
| Keywords | online learning / speech recognition / speech synthesis / autonomy |
|---|
| Outline of Annual Research Achievements |
The purpose of this project is to investigate how learners of English can use online speech recognition and synthesis to improve spoken language and autonomy, and to improve spoken assessment.
The 4th year plan was to assess and further develop the accuracy of speech recognition and synthesis systems in both personal-computer based and mobile-based systems across major operating systems.
A major aspect of Speech Recognition is its ability to transcribe spoken words to machine readable text. Since the project has generated a large number of utterances a secondary goal was to develop storage and data analysis techniques such as tokenization and corpora mining to analyze patterns and usage for learners of language and compare them with native non-learners. This analysis is still ongoing and has formed the basis of further research.
The results of the primary goals and developments were presented with a presentation at the JALT CALL 2021 Online Conference (Japan), and at the JALT 2021 International Online Conference (Japan), and at the Kotesol 2021 International Online Conference (Korea). (Due to Covid-19 travel restrictions planned presentations at overseas conferences were curtailed.)
|
