The 72nd In Silico Megabank Research Seminar will be held on Tuesday, January 26, 2016. This Time, we will be welcoming Dr. Ryu Takeda, The Institute of Scientific and Industrial Research, Osaka University as our lecturer, and he will be speaking on “Recent Machine Learning and Component Technology for Speech Dialog System”.
・Date/Time: January 26 (Tuesday) 5:00 pm‐6:30 pm
・Venue: Small Conference Room 2(3rd Floor), Tohoku Medical Megabank Building
・Title: Recent Machine Learning and Component Technology for Speech Dialog System
・Lecturer: Ryu Takeda（The Institute of Scientific and Industrial Research, Osaka University）
＊This lecture is transferable as a class in the medical research-related lecture course.
・Abstract: A speech dialog system is a system that understands and corresponds to human voice questioning to it. Such system is applied to the interface of mobile terminals (Siri), robots (Pepper), and so on. At our laboratory, we conduct studies focusing not only on the linguistic understanding of user speech but on hierarchical understanding of speech behavior and mutual adaptation between system and user. For these types of studies machine learning is an inevitable technology, and it is widely used from signal processing, and voice recognition to the core dialog strategy and user model learning. In this seminar, challenges and necessary technologies for speech dialog system and application of machine learning technology including our study cases will be introduced. In addition, examples of the application of recent Deep Learning in component technology and my approaches and efforts are also introduced.
・Organizer: Kaname Kojima, Masao Nagasaki