• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Asia-Pacific Signal and Information Processing Association Annual Summit and Conference >Development and Operation of Speech-Oriented Information Guidance Systems, Kita-chan and Kita-robo
【24h】

Development and Operation of Speech-Oriented Information Guidance Systems, Kita-chan and Kita-robo

机译：面向语音的信息指导系统Kita-chan和Kita-robo的开发和运营

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The authors have been operating a real-environment speech-oriented information guidance system named “Takemarukun” daily at the Ikoma City North Community Center. The system introduces an example-based one-question-one-answer strategy, noise rejection and an adult versus child user discrimination mechanism. As a result, it realizes robust response generation since its initial operation in Nov. 2002. Following the success of “Takemaru-kun”, two additional systems were developed and installed in a railway station, side by side, since Apr. 2006. Although the three systems share the same core software, “Takemaru-kun” and “Kita-chan” employ CG agents and “Kita-robo” has a robot-like body casing. At the railway station, users can talk to the system of their preference. In this paper, we introduce the two later information guidance systems and report their initial operational results including an analysis of user utterances according to age groups. An analytical result shows that children’s utterances to the robot are twice as many as those to the CG agent. In addition to that, it is observed that children do not make difference in question topics between the systems, but adults do.
机译：作者每天在生驹市北社区中心运行名为“ Takemarukun”的面向现实环境的面向语音的信息指导系统。该系统引入了基于示例的“一问一答”策略，噪声抑制以及成人与儿童用户区分机制。因此，自2002年11月首次投入运营以来，它便实现了强大的响应生成能力。继“ Takemaru-kun”成功之后，自2006年4月起，又并排开发了两个附加系统，并并排安装在火车站中。这三个系统共享相同的核心软件，“ Takemaru-kun”和“ Kita-chan”使用CG代理，而“ Kita-robo”则具有类似机器人的机壳。在火车站，用户可以与自己喜欢的系统进行交谈。在本文中，我们介绍了两个后来的信息指导系统，并报告了它们的初始操作结果，包括根据年龄段对用户话语进行的分析。分析结果表明，儿童对机器人的说话量是对CG特工的说话量的两倍。除此之外，还可以观察到，儿童在系统之间的问题主题上并没有什么区别，而成年人则有所不同。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号