| Co-Investigator(Kenkyū-buntansha) |
KOMATANI Kazunori 名古屋大学, 工学(系)研究科(研究院), 准教授 (40362579)
NANJO Hiroaki 龍谷大学, 理工学部, 助教 (50388162)
NISIMURA Ryuuichi 和歌山大学, システム工学部, 助教 (00379611)
NISHIDA Masafumi 同志社大学, 理工学部, 准教授 (80361442)
SHINOZAKI Takahiro 東京工業大学, 総合理工学研究科(研究院), 准教授 (80447903)
AKITA Yuya 京都大学, 学内共同利用施設等, 助教 (90402742)
|
|---|
| Budget Amount *help |
¥17,550,000 (Direct Cost: ¥13,500,000、Indirect Cost: ¥4,050,000)
Fiscal Year 2013: ¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000)
Fiscal Year 2012: ¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000)
Fiscal Year 2011: ¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
Fiscal Year 2010: ¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
Fiscal Year 2009: ¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
|
|---|
| Research Abstract |
This study focuses on developing a framework that integrates handling of multiple knowledge layer from speech signal processing to spoken language understanding directly into speech recognition process in a statistical mannar. Statistical models at layers of language model, acoustic model and dialogue model are widely investigated. For integration, speech decoding based on Bayes-risk minimization in which all the constraint can be expressed as Bayes risk, and some integration methods that utilizes speech information for dialogue management and turn taking was investigated. Part of the results are publicly available as part of an open-source voice interaction building tool MMDAgent and Julius.
|
