首页> 外国专利> VOICE RECOGNITION DEVICE AND NONINSTRUCTION AND/OR ON- LINE ADAPTING METHOD FOR AUTOMATIC VOICE RECOGNITION DEVICE

VOICE RECOGNITION DEVICE AND NONINSTRUCTION AND/OR ON- LINE ADAPTING METHOD FOR AUTOMATIC VOICE RECOGNITION DEVICE

机译:语音识别装置和自动语音识别装置的非指令和/或在线自适应方法

摘要

PROBLEM TO BE SOLVED: To increase the recognition rate of the voice recognition device.;SOLUTION: An D/A converter 12 converts an analog voice signal from a microphone into a digital voice signal and a feature extractor switch 13 extracts a feature vector from the digital voice signal. A recognizer 14 recognizes the speaking of a user according to the feature vector and a set of speaker adaptive models and/or speaker independent models, and an adapter 17 is supplied with the recognition result and generates and/or adapts the set of speaker adaptive models. A decision unit 21 supplies the adapter 17 with a signal indicating whether an arbitrary received word is used for the generation and/or adaptation of the set of the speaker adaptive models.;COPYRIGHT: (C)2000,JPO
机译:解决的问题:为了增加语音识别设备的识别率。解决方案:D / A转换器12将来自麦克风的模拟语音信号转换为数字语音信号,并且特征提取器开关13从语音提取器中提取特征向量。数字语音信号。识别器14根据特征向量和一组说话者自适应模型和/或与说话者无关的模型来识别用户的说话,并且适配器17被提供有识别结果,并生成和/或适配该说话者自适应模型。 。判定单元21向适配器17提供信号,该信号指示是否使用任意接收到的单词来生成和/或调整说话者自适应模型的集合。;版权:(C)2000,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