首页> 外国专利> Electronic device, identification method, system and computer-readable storage medium

Electronic device, identification method, system and computer-readable storage medium

机译:电子设备,识别方法,系统和计算机可读存储介质

摘要

The present invention relates to an electronic device, an identity verification method, a system, and a computer-readable storage medium, wherein the electronic device includes a memory and a processor, an identity verification system is stored in the memory, and the identity verification system is performed by the processor. After receiving the current voice data of the target user to be executed and verifying the identity, framing the current voice data according to a preset framing parameter to obtain a plurality of voice frames, and using a predetermined filter Extracting a preset type of acoustic feature from each voice frame and generating a plurality of observation feature units corresponding to the current voice data according to the extracted acoustic features, and pre-stored observation feature units The step of obtaining a paired observation feature unit of a plurality of groups by pairing each with two, and inputting and outputting the identification verification result to a pre-set type identity verification model generated by training in advance the observation feature units paired with a plurality of groups. Acquires a step to verify the identity of this target user. The present invention can reduce the error rate of voice identification.
机译:电子设备,身份验证方法,系统和计算机可读存储介质技术领域本发明涉及一种电子设备,身份验证方法,系统和计算机可读存储介质,其中,电子设备包括存储器和处理器,在该存储器中存储身份验证系统,并且该身份验证系统由处理器执行。在接收到要执行的目标用户的当前语音数据并验证身份后,根据预设的成帧参数对当前语音数据进行成帧,以获得多个语音帧,并使用预定的过滤器从中提取预设的声学特征类型。每个语音帧,并根据提取的声学特征,生成与当前语音数据相对应的多个观察特征单元;以及预先存储的观察特征单元。通过将每一个与两个配对来获得多个组的成对观察特征单元的步骤然后,将识别验证结果输入并输出到通过预先训练与多个组配对的观察特征单元而生成的预设类型身份验证模型。获取验证该目标用户身份的步骤。本发明可以降低语音识别的错误率。

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