2022 Fiscal Year Annual Research Report
Cross-disciplinary approach to prosody-based automatic speech processing and its application to computer-assisted language teaching
| Project/Area Number |
20K00838
|
|---|
| Research Institution | The University of Aizu |
|---|
Principal Investigator |
Pyshkin Evgeny 会津大学, コンピュータ理工学部, 上級准教授 (50794088)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
Mozgovoy Maxim 会津大学, コンピュータ理工学部, 准教授 (60571776)
BLAKE John 会津大学, コンピュータ理工学部, 上級准教授 (80635954)
|
|---|
| Project Period (FY) |
2020-04-01 – 2023-03-31
|
| Keywords | multi-language CAPT / suprasegmentals / proximal developement / CAPT personalization / pitch visualization |
|---|
| Outline of Annual Research Achievements |
In practical perspective, (1) the repetitive attempts pitch display module has been implemented; (2) the voice activity detection algorithm has been tested and adjusted to assure correct catch of the beginning of speech; (3) the components of StudyIntonation CAPT environment have been extended and assessed to support tonal language pronunciation training (Vietnamese) with a possibility to pitch graph segmentation for differentiation between phrasal intonation and specific tone mastering; (4) pilot versions of the beginner course for mora-timed language (Japanese) have been designed.
For theory, (1) longitudinal and microgenetic analysis of L2 pronunciation development has been conducted based on Vygotskian sociocultural theory concepts, thus, providing rationale for scaffolding learners through their zone of proximal development; (2) corpus comprising 1050 speech records labelled with orthographic transcript, pitch readings, and similarity metrics have been constructed for quantitative evaluation of learners' progress with using dynamical modeling and cross-recurrence quantification analysis; (3) accent recognition possibilities for further personalization of CAPT feedback have been studied.
|
