首页> 外国专利> DEVICE AND METHOD FOR CONTROL BY SPEECH RECOGNITION, CONTROLLED SYSTEM UNIT, SYSTEM FOR USING CONTROL BY SPEECH RECOGNITION AND STORAGE MEDIUM RECORDING PROGRAM FOR CONTROL BY SPEECH RECOGNITION

DEVICE AND METHOD FOR CONTROL BY SPEECH RECOGNITION, CONTROLLED SYSTEM UNIT, SYSTEM FOR USING CONTROL BY SPEECH RECOGNITION AND STORAGE MEDIUM RECORDING PROGRAM FOR CONTROL BY SPEECH RECOGNITION

机译:语音识别控制的装置和方法,受控系统单元,用于语音识别的控制系统和用于语音识别的存储介质记录程序

摘要

PROBLEM TO BE SOLVED: To report the presence of invalid speaking to a user when there is such speaking invalid for the current state of a controlled system. ;SOLUTION: An operating state output part 211 or 221 sends information concerning the state to a voice recognizing device 23. Based on the information, an audio state analytic part 234 sets a flag corresponding to the information in a table T. When any phrase is recognized from a voice by a pattern matching part 236, the audio state analytic part 234 judges whether the recognized phrase is valid or not in the current state. When that phrase is judged invalid, a caution output part 235 issues a caution to the user. The user can comprehend that the phrase is not recognized but it is not suitable, the speaking of a right phrase is facilitated without repeating an incorrect instruction, and a user interface is improved.;COPYRIGHT: (C)1999,JPO
机译:要解决的问题:当受控系统的当前状态存在无效的说话时,向用户报告是否存在无效的说话。 ;解决方案:操作状态输出部分211或221将与状态有关的信息发送到语音识别设备23。音频状态分析部分234基于该信息在表T中设置与该信息相对应的标志。音频状态分析部分234通过模式匹配部分236从语音中识别出声音,从而判断识别出的短语在当前状态下是否有效。当判断该短语无效时,警告输出部分235向用户发布警告。用户可以理解该短语未被识别但是不合适,可以在不重复错误指令的情况下帮助说出正确的短语,并且可以改善用户界面。;版权所有:(C)1999,JPO

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

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