Project/Area Number |
24650085
|
Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
Allocation Type | Single-year Grants |
Research Field |
Perception information processing/Intelligent robotics
|
Research Institution | Wakayama University |
Principal Investigator |
|
Co-Investigator(Kenkyū-buntansha) |
MORISE Masanobu 山梨大学, 大学院医学工学総合研究部, 助教 (60510013)
|
Project Period (FY) |
2012-04-01 – 2014-03-31
|
Project Status |
Completed (Fiscal Year 2013)
|
Budget Amount *help |
¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2013: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2012: ¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
|
Keywords | 音声合成 / 音声知覚 / 音声コミュニケーション / 音声インタフェース / 非言語 / インタフェース / モーフィング / 音声変換 / 機能音声 / 音声分析 / 主観評価実験 / 脳活動 / 潜在知覚 / 一般化線形モデル |
Research Abstract |
Aiming at establishing a design methodology of voice attributes to facilitate understanding, affection, alert and safety feeling by non-linguistic voice aspects, this research project was conducted. It was based on a de facto standard speech research framework STRAIGHT, developed by the prime investigator and yielded several useful research tools. A highly accurate and computationally efficient F0 extractor with higher temporal resolution than conventional methods is an example of such extension and development. In this course of investigations, a revolutionary new morphing framework was invented. The new method is capable of morphing arbitrary many voice examples in one shot procedure with individual control of each physical speech parameter and enabled time dependent weight setting. This new morphing method and other research products of the project provides basis of the substantially new research project.
|