2020 Fiscal Year Research-status 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 to improve spoken assessment. The 3rd year plan was to develop a spaced learning system, to further update the interface, and to develop an analysis system of the word parsing engine to improve the accuracy of the speech recognition system.
Although not all the research goals were met, as noted below the results of these developments were presented with a presentation at the JALTCALL 2020 Online Conference, and was part of an invited talk at the PanSIG 2020 Online Conference.
|
| Current Status of Research Progress |
Current Status of Research Progress
3: Progress in research has been slightly delayed.
Reason
Due to a medical emergency in July to the lead researcher that required hospitalization and subsequent rehabilitation, some of the research goals for 2020-21 were unable to be completed. Furthermore, the Covid-19 situation meant that overseas conferences were cancelled or travel was restricted. However, this work will be carried out in 2021-22.
The spaced repetition research was not completed but there were major updates to the system that will enable this work to be the focus of this year.
|
| Strategy for Future Research Activity |
A major goal for this year is to complete the study on the pronunciation and vocabulary acquisition through the use of spaced repetition. Furthermore, an in-depth analysis of the data collated from the spoken practices will be analysed for patterns to ascertain common mistakes and overall speaking patterns of Japanese students.
These studies will be carried out at 2 institutions: Kanazawa University, and the University of Shimane.
|
| Causes of Carryover |
The major expenses are
* a computer for analysis of the speech patterns; hiring of an assistant to help with data input and checking; server rental expenses; travel expenses (overseas if possible)
|
