首页> 外国专利> Method of supporting proofreading of a recognized text in a speech to text system with playback speed adapted to confidence of recognition

Method of supporting proofreading of a recognized text in a speech to text system with playback speed adapted to confidence of recognition

机译:支持语音到文本系统中的已识别文本的校对的方法,其回放速度适合于识别的置信度

摘要

Text (2) is received from a voice signal (1) via voice recognition. Text components (B1-B5) of this text have a reliability rate (3) for their correctness. Using the reliability rate of the text components forms a course for a playback speed (12) for the voice signal's part relating to the text components. Quicker playing of reliable passages in the voice signal shortens the operating time needed for proof reading, while slow playing of unreliable passages expedites the concentration of a user doing the proof reading. Independent claims are also included for a device for assisting with proof reading of text received via voice recognition in a voice signal, for a voice recognition system to operate with this device and for a method for assisting with proof reading of text received through conversion from a voice signal into a written form.
机译:经由语音识别从语音信号(1)接收文本(2)。此文本的文本组件(B1-B5)的正确性可靠率(3)。使用文本分量的可靠​​性比率形成与文本分量有关的语音信号部分的回放速度(12)的过程。语音信号中可靠段落的更快播放缩短了校对所需的操作时间,而不可靠段落的缓慢播放则加快了用户进行校对的注意力。还包括独立权利要求,用于辅助对语音信号中经由语音识别接收的文本进行校对的设备,用于与该设备一起操作的语音识别系统以及用于辅助对通过从语音信箱转换而接收的文本进行校对的方法。语音信号转换成书面形式。

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