Generation of presentation motion using sequence to sequence model
-
- SHIMAZU Akihito
- The University of Electro-Communications
-
- HIEIDA Chie
- The University of Electro-Communications
-
- NAGAI Takayuki
- The University of Electro-Communications
-
- NAKAMURA Tomoaki
- The University of Electro-Communications
-
- TAKEDA Yuki
- Dai Nippon Printing Co., Ltd.
-
- HARA Takenori
- Dai Nippon Printing Co., Ltd.
-
- NAKAGAWA Osamu
- Dai Nippon Printing Co., Ltd.
-
- MAEDA Tsuyoshi
- Dai Nippon Printing Co., Ltd.
Bibliographic Information
- Other Title
-
- 系列変換モデルを用いたプレゼンテーション動作の生成
Abstract
<p>In the presentation, gestures play a very important role as a means of improving the information transmission effect. Moreover, it was shown that the movement expressing the enthusiasm and intention of the presenter in an unconscious manner affects the success of the presentation and the impression on the audience. For these reasons, it is required for presentation robots to perform such movements; however, manual design of these movements is not an easy task. In this research, we propose a method to learn relationship between speech prosodic information and motion using a sequence to sequence model, and directly generate appropriate motions from prosodic information. This paper also proposes a method for generating motions representing meanings of specific words.</p>
Journal
-
- Proceedings of the Annual Conference of JSAI
-
Proceedings of the Annual Conference of JSAI JSAI2018 (0), 2G103-2G103, 2018
The Japanese Society for Artificial Intelligence
- Tweet
Details 詳細情報について
-
- CRID
- 1390001288047407872
-
- NII Article ID
- 130007423913
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- CiNii Articles
-
- Abstract License Flag
- Disallowed