| 研究課題/領域番号 |
20K11956
|
|---|
| 研究機関 | 会津大学 |
|---|
研究代表者 |
Julian Villegas 会津大学, コンピュータ理工学部, 准教授 (50706281)
|
|---|
| 研究分担者 |
李 勝勲 国際基督教大学, 教養学部, 准教授 (20770134)
MARKOV K 会津大学, コンピュータ理工学部, 教授 (80394998)
|
|---|
| 研究期間 (年度) |
2020-04-01 – 2023-03-31
|
| キーワード | Phonation prediction / Machine Learning / Psychoacoustics |
|---|
| 研究実績の概要 |
During 2020, we progressed on the acquisition of corpora by an extensive bibliography review on Zapotec and related languages that are characterized by a three-way phonemic contrast (e.g. normal, creaky, and breathy). We also advanced on implementation and evaluation of psychoacoustic models by 1) identifying auditory models from which we could extract features and 2) tabulating subjective results from published studies. In addition, we have conducted subjective experiments to compare how naive, native, and expert classifications compare. As a result of these activities, we have produced two pieces of software: one for easing the process of extracting features from EGG recordings, and another one used for experts to classify tokens
|
| 現在までの達成度 (区分) |
現在までの達成度 (区分)
2: おおむね順調に進展している
理由
Despite not being able to do field work as a consequence of the measures to prevent the spreading of COVID-19, we have managed to accomplish the tasks programmed for the first year.
|
| 今後の研究の推進方策 |
During this fiscal year, we will focus on the acquisition and annotation of spoken corpora, the development of the machine learning models and publishing results of the classification comparisons obtained in the first year.
|
| 次年度使用額が生じた理由 |
It was no possible to travel to Mexico last year for the fieldwork. This was due to the travel restrictions imposed to prevent the spread of COVID-19. We expect to conduct fieldwork this year depending on the evolution of the pandemic In Japan and Mexico.
|
