-
公开(公告)号:US5093855A
公开(公告)日:1992-03-03
申请号:US402495
申请日:1989-09-01
申请人: Emmeran Vollert , Goerg Humpert
发明人: Emmeran Vollert , Goerg Humpert
CPC分类号: H04M3/382 , H04M1/66 , H04Q11/0471 , H04M2201/40 , H04Q2213/095 , H04Q2213/332 , H04Q2213/378 , H04Q2213/392
摘要: A method and apparatus for speaker recognition in a telephone switching system. For speaker recognition in, in particular, a system fashioned as an ISDN communications system, speech specimens are input into a telephone terminal equipment (T1, T2) and are pre-processed there, being, in particular, sampled with a sampling rate that is doubled in comparison to the usual sampling rate. The samples are transmitted to a switching system (VA) in the two ISDN data channels (B1, B2) in alternation, the actual speaker recognition (SPR) being carried out in this switching system (VA).
摘要翻译: 一种用于电话交换系统中的说话者识别的方法和装置。 对于特别是作为ISDN通信系统的系统的话音识别,将语音标本输入到电话终端设备(T1,T2)中,并在那里进行预处理,特别是以采样率采样 与通常的抽样率相比翻了一倍。 样本被交替传输到两个ISDN数据信道(B1,B2)中的交换系统(VA),在该交换系统(VA)中执行实际的说话者识别(SPR)。