首页> 外国专利> performance improvement based on the negative examples for speech recognition (anti-word)

performance improvement based on the negative examples for speech recognition (anti-word)

机译:基于语音识别(反词)负面示例的性能改进

摘要

The system and method for the negative examples based on performance improvements to the speech recognition is presented. Embodiments of the present disclosure, the automatic speech recognition (ASR) systems, and erroneously detected to be identified, and, to deal with the identification of the negative examples of keywords. Various methods may be used to identify the negative examples of keywords. Such methods may include, for example, a negative example that up and allow learning to listen by the human from the field-specific large text source. In at least one embodiment, the negative examples of keywords may be used to improve the performance of the ASR system by reducing false positives.BACKGROUND 1
机译:提出了基于语音识别性能改进的反例系统和方法。在本公开的实施例中,自动语音识别(ASR)系统被错误地检测并被识别,并且用于处理关键词否定示例的识别。可以使用各种方法来识别关键字的否定示例。这样的方法可以包括例如否定示例,该否定示例可以提高并允许人类从特定于现场的大文本源中学习收听。在至少一个实施例中,关键词的否定示例可以用于通过减少误报来改善ASR系统的性能。背景1

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