2023 Fiscal Year Final Research Report
Foundation of speech communication support based on auditory perception models for everyone including elderly persons with hearing impairment
| Project/Area Number |
21H03468
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 61010:Perceptual information processing-related
|
|---|
| Research Institution | Wakayama University |
|---|
Principal Investigator |
Irino Toshio 和歌山大学, システム工学部, 教授 (20346331)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
松井 淑恵 豊橋技術科学大学, 次世代半導体・センサ科学研究所, 教授 (10510034)
小林 洋介 室蘭工業大学, 大学院工学研究科, 准教授 (10735103)
坂野 秀樹 名城大学, 情報工学部, 教授 (20335003)
|
|---|
| Project Period (FY) |
2021-04-01 – 2024-03-31
|
| Keywords | 高齢難聴 / 模擬難聴 / 音声了解度 / 客観評価指標 / 主観評価実験 / 音声分析合成 / 聴覚情報処理 |
|---|
| Outline of Final Research Achievements |
We derived several innovative results in this study. We proposed that the frequency selectivity of the auditory periphery can be estimated with high accuracy using the gammachirp filter and also further advanced the gammachirp filterbank GCFB. We scraped and rebuilt our hearing loss simulator WHIS based on GCFB. WHIS was shown to outperform conventional methods in objective distortion measures and sound quality listening experiments. Speech intelligibility (SI) experiments were also conducted with WHIS to show that only the peripheral hearing loss factors can be discussed separately from the subsequent auditory factors. A new objective measure, GESI, was developed to predict SI in older people with hearing loss and was shown to explain subjective SI results from both crowdsourced remote and well-controlled laboratory experiments better than conventional methods.
|
| Free Research Field |
聴覚計算理論/心理実験/音信号処理
|
| Academic Significance and Societal Importance of the Research Achievements |
お年寄りに音声の言語内容がどの程度伝わるかを予測する、新しい音声了解度客観指標GESIを開発できた。音声強調処理の客観評価指標は従来健聴者しか想定していなかったが、これを高齢難聴者まで対象を広げることができた。 また、模擬難聴システムWHISも従来手法より高音質のため、従来からの音声了解度だけではなく多様な聴覚心理実験に活用可能と考えられる。これらの手法は、補聴器信号処理や、聴覚音声支援システムの今後の開発に活用できるであろう。高齢者にとって聞き取り易い音声や音響信号は、若年健聴者にとっても明瞭に聴こえるはずで、音のインクルーシブデザインに貢献できると考えられる。
|
