| Project/Area Number |
26280063
|
|---|
| 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 | Doshisha University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
渡辺 秀行 株式会社国際電気通信基礎技術研究所, その他部局等, 研究員 (40395091)
中村 篤 名古屋市立大学, 大学院システム自然科学研究科, 教授 (50396206)
Delcroix Marc 日本電信電話株式会社NTTコミュニケーション科学基礎研究所, 協創情報研究部, 主任研究員 (70793339)
小川 厚徳 日本電信電話株式会社NTTコミュニケーション科学基礎研究所, メディア情報研究部, 主任研究員 (90527516)
吉岡 拓也 日本電信電話株式会社NTTコミュニケーション科学基礎研究所, メディア情報研究部, 研究主任 (40466404)
堀 貴明 日本電信電話株式会社NTTコミュニケーション科学基礎研究所, メディア情報研究部, 主任研究員 (20396211)
|
|---|
| Project Period (FY) |
2014-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥15,990,000 (Direct Cost: ¥12,300,000、Indirect Cost: ¥3,690,000)
Fiscal Year 2017: ¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2016: ¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2015: ¥3,510,000 (Direct Cost: ¥2,700,000、Indirect Cost: ¥810,000)
Fiscal Year 2014: ¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
|
|---|
| Keywords | パターン認識 / 識別学習 / 最小分類誤り学習 / カーネル法 / ニューラルネットワーク / 音声認識 / 機械学習 / 深層学習 |
|---|
| Outline of Final Research Achievements |
Aiming at the development of highly discriminative feature space, of which corresponding classification error probability is as small as possible, we developed the following new technologies: a Dynamic-Time-Warping (DTW)-based geometric margin for variable-length patterns, Large Geometric Margin Minimum Classification Error training using the DTW-based geometric margin, a compact kernel classifier using Kernel Minimum Classification Error training, speaker and environment adaptation methods for deep-neural-network-based speech recognizers using Speaker Adaptive Training and auxiliary neural network, and fast search methods for large scale speech recognizers. In addition, we opened a new venue for a new pattern recognizer training method that does not require hyper-parameters but is based on Bayes boundary-ness, which is defined using the ambiguity in classification decision around estimated class boundaries.
|
