公开(公告)号：EP0528990A4

公开(公告)日：1994-06-08

申请号：EP91911300

申请日：1991-05-14

Applicant: VCS IND INC D B A VOICE CONTRO

Inventor： HUNT ALAN K ,  SCHALK THOMAS B

IPC: G07C9/00 ,  G10L15/10 ,  G10L15/22 ,  G10L17/00 ,  H04M3/38 ,  G10L5/06

CPC classification number: G10L17/24 ,  G07C9/00158 ,  G10L15/10 ,  G10L2015/0631 ,  H04M3/382 ,  H04M2201/40

公开(公告)号：EP0671043A4

公开(公告)日：1996-03-20

申请号：EP94902380

申请日：1993-11-24

Applicant: VCS IND INC D B A VOICE CONTRO

Inventor： HUNT ALAN K ,  SCHALK THOMAS B

IPC: G07C9/00 ,  G10L17/00 ,  H04M3/38 ,  G10L9/08 ,  H04M1/66

CPC classification number: G07C9/00142 ,  G06F21/32 ,  G06F21/40 ,  G06F21/83 ,  G06F2221/2105 ,  G06F2221/2113 ,  G06F2221/2117 ,  G07C9/00158 ,  G10L17/00 ,  G10L17/22 ,  G10L17/24 ,  H04M3/382 ,  H04M2201/40

Abstract: A method for enabling a caller to obtain access to one or more services via a telephone network by speaking a password begins by establishing at least one predetermined threshold value for a speaker verification signal. For each spoken character of the password, the method generates a set of parameters using a voice verification feature transformation. After entry and recognition of the password, the sets of parameters are used to generate a speaker verification signal for the password (step 78). Upon the occurence of a predetermined call condition, the predetermined threshold value is adjusted to increase the level of security in the verification algorithm. If the speaker verification signal for the password has a predetermined relationship with respect to the adjusted threshold value (84), the caller's identity is accepted (88). If not, the caller may be asked (90) to answer certain personnal questions before his or her identity is accepted.

Abstract translation: 描述了一种使呼叫者能够通过说出口令通过电话网络获得对一个或多个服务的访问的方法。 该方法开始于为扬声器验证信号建立至少一个预定阈值。 对于密码的每个口头字符，该方法使用语音验证特征变换生成一组参数。 在输入和识别密码之后，使用这些参数来生成用于密码的扬声器验证信号。 在发生预定呼叫条件时，调整预定阈值以增加验证算法中的安全级别。 如果密码的信号验证信号相对于经调整的阈值具有预定的关系，则接受呼叫者的身份。 如果不是，可以要求来电者在接受他或她的身份之前回答某些个人问题。

公开(公告)号：ES2141090T3

公开(公告)日：2000-03-16

申请号：ES91911300

申请日：1991-05-14

Applicant: VCS IND INC D B A VOICE CONTRO

Inventor： HUNT ALAN K ,  SCHALK THOMAS B

IPC: G07C9/00 ,  G10L15/10 ,  G10L15/22 ,  G10L17/00 ,  H04M3/38 ,  G10L5/06 ,  H04M1/64 ,  H04M1/66 ,  G10L3/00

Abstract: A caller is prompted to enunciate (105) an alphanumeric phrase comprising a number of characters. Having reset (104) to zero a cumulative recognition distance register or its equivalent, each character is captured and analyzed (106) and a form of acoustic dissimilarity calculated (108) in relation to a previously stored and corresponding reference character of a reference alphanumeric string. The register is incremented by a quantified difference between the reference character and the captured character and then an assessment (112) is made to determine which of the reference alphanumeric strings has the lowest cumulative recognition distance implying that this was the alphanumeric phrase spoken by the caller. Robust phrase recognition is thus achieved by the exemplified methodology of Figure 6.

公开(公告)号：AU649688B2

公开(公告)日：1994-06-02

申请号：AU7995891

申请日：1991-05-14

Applicant: VCS IND INC D B A VOICE CONTRO

Inventor： HUNT ALAN K ,  SCHALK THOMAS B

IPC: G07C9/00 ,  G10L15/10 ,  G10L15/22 ,  G10L17/00 ,  H04M3/38 ,  G10L5/06 ,  H04M1/64 ,  H04M1/66

Abstract: A caller is prompted to enunciate (105) an alphanumeric phrase comprising a number of characters. Having reset (104) to zero a cumulative recognition distance register or its equivalent, each character is captured and analyzed (106) and a form of acoustic dissimilarity calculated (108) in relation to a previously stored and corresponding reference character of a reference alphanumeric string. The register is incremented by a quantified difference between the reference character and the captured character and then an assessment (112) is made to determine which of the reference alphanumeric strings has the lowest cumulative recognition distance implying that this was the alphanumeric phrase spoken by the caller. Robust phrase recognition is thus achieved by the exemplified methodology of Figure 6.

公开(公告)号：CA2138774A1

公开(公告)日：1994-01-06

申请号：CA2138774

申请日：1993-06-22

Applicant: VCS IND INC D B A VOICE CONTRO

Inventor： HUNT ALAN K ,  SCHALK THOMAS B

IPC: G07C9/00 ,  G10L17/00 ,  H04M3/38 ,  G10L9/08 ,  H04M1/66

Abstract: The present invention describes a method for recognizing alphanumeric strings spoken over a telephone network (10) wherein individual character recognition need not to be uniformly high in order to achieve high string recognition accuracy. Preferably, the method uses a processing system (14) having a digital processor, an interface (42) to the telephone network (10), and a database (32) for storing a predetermined set of reference alphanumeric strings. In operation, the system (10) prompts the caller to speak the characters of a string, and characters are recognized using a speaker-independent voice recognition algorithm (48). The method calculates recognition distances between each spoken input character and the corresponding letter or digit in the same position within each reference alphanumeric string. After each character is spoken (206), captured and analyzed (208), each reference string distance is incremented (204) and the process is continued, accumulating distances for each reference string, until the last character is spoken. The reference string with the lowest cumulative distance is then declared to be the recognized string (210).