| Project/Area Number |
17K00258
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Perceptual information processing
|
|---|
| Research Institution | National Institute of Advanced Industrial Science and Technology |
|---|
Principal Investigator |
Sasou Akira 国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 研究グループ長 (50318169)
|
|---|
| Project Period (FY) |
2017-04-01 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2019)
|
| Budget Amount *help |
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2019: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2018: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2017: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
|
|---|
| Keywords | 音声分析 / 食道発声音声 / 声質改善 / AR-HMM / 感情音声 / 音声情報処理 |
|---|
| Outline of Final Research Achievements |
The main purpose of this research project is to realize a speech analysis method applicable to various types of speech including not only a normal voice uttered by a periodic excitation source due to vocal cord vibration but also special voice such as an esophageal voice uttered by a non-stationary, non-periodic excitation source due to vibration at the upper part of the esophagus. We constructed a new voice analysis method that can automatically generate the optimal topology of the HMM that represents the excitation source from the observed voice signal, and can also simultaneously estimate the model parameters. Based on the proposed speech analysis method, we then investigated the feasibility of voice quality enhancing method to replace the excitation source, which is the voice quality deterioration factor of the esophageal voice, with a vocal cord excitation source estimated from the normal voice recorded before total laryngectomy and resynthesize it.
|
| Academic Significance and Societal Importance of the Research Achievements |
音声は最も重要なコミュニケーション手段であり、高齢者のみならず人が充実した社会生活を送るために重要な要素である。しかし、喉頭がんの進行などにより喉頭全摘出手術を余儀なくされ、自分の声を失う高齢者は少なくない。本研究課題で実現を目指す声質改善装置は、不幸にして自分の声を失った人が、手術前の自分の声に近い発声を取り戻し、再度、自信をもって声による人とのコミュニケーションをとれるようにすることで、積極的な社会参加を促すことを目的とする。また、声帯音源で発声する健常者音声の分析手法は従来多く提案されているが、食道発声音声のような音声を対象としたものは決して多くない。
|
