Analysis of long-term and large-scale experiments on robot dialogues using a cloud robotics platform

Komei Sugiura, Koji Zettsu

研究成果: Conference contribution

2 被引用数 (Scopus)

抄録

To build conversational robots, roboticists are required to have deep knowledge of both robotics and spoken dialogue systems. Unlike using stand-alone speech recognition/ synthesis toolkits, a cloud robotics platform for humanrobot communication enables high-quality speech recognition and synthesis that is optimized to human-robot interactions. This is challenging because we need to build a wide variety of functionalities ranging from a stable cloud platform to highquality multilingual speech recognition and synthesis engines. From this background, we constructed rospeex [1], which is a cloud robotics platform for multilingual spoken dialogues with robots. Over 20,000 unique users have used rospeex in the two years since it was launched. In this paper, we propose a method to reduce the response time in rospeex; and analyze its effectiveness. We also analyze the server logs of rospeex that we have collected.

本文言語English
ホスト出版物のタイトルHRI 2016 - 11th ACM/IEEE International Conference on Human Robot Interaction
出版社IEEE Computer Society
ページ525-526
ページ数2
ISBN(電子版)9781467383707
DOI
出版ステータスPublished - 2016 4 12
外部発表はい
イベント11th Annual ACM/IEEE International Conference on Human-Robot Interaction, HRI 2016 - Christchurch, New Zealand
継続期間: 2016 3 72016 3 10

出版物シリーズ

名前ACM/IEEE International Conference on Human-Robot Interaction
2016-April
ISSN(電子版)2167-2148

Conference

Conference11th Annual ACM/IEEE International Conference on Human-Robot Interaction, HRI 2016
国/地域New Zealand
CityChristchurch
Period16/3/716/3/10

ASJC Scopus subject areas

  • 人工知能
  • 人間とコンピュータの相互作用
  • 電子工学および電気工学

フィンガープリント

「Analysis of long-term and large-scale experiments on robot dialogues using a cloud robotics platform」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル