2017 Fiscal Year Final Research Report
Self-Organized Learning of Speech Recognition and Synthesis Systems
| Project/Area Number |
26280055
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Partial Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Perceptual information processing
|
|---|
| Research Institution | Tokyo Institute of Technology |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
能勢 隆 東北大学, 工学研究科, 准教授 (90550591)
Duh Kevin 奈良先端科学技術大学院大学, 情報科学研究科, 助教 (80637322)
|
|---|
| Co-Investigator(Renkei-kenkyūsha) |
ARAI Takayuki 上智大学, 理工学部・情報理工学科, 教授 (80266072)
|
|---|
| Research Collaborator |
WATANABA Shinji
DUH Kevin
|
|---|
| Project Period (FY) |
2014-04-01 – 2018-03-31
|
| Keywords | 音声言語情報処理 / 深層学習 / モデル構造最適化 / 半教師あり学習 / 高性能音声認識システム / 強化学習 / ブラックボックス最適化 / 進化的アルゴリズム |
|---|
| Outline of Final Research Achievements |
The purpose of this study is to make self-standing speech and language information processing systems that can learn from a small amount of labeled and a significant amount of unlabeled speech data as well as can automatically optimize its structure and learning conditions. We have proposed evolution strategy based automation method for neural network-based system development, series of semi-supervised learning methods for statistical speech models, and a reinforcement learning method of speech recognition systems. A high-performance Japanese speech recognition system integrating the research results have been published and widely used.
|
| Free Research Field |
音声言語情報処理
|
