Voice-controlled account access over a telephone network
First Claim
1. A method for enabling a caller to obtain access to one or more services via a telephone network by speaking first and second character strings each having a plurality of characters, comprising the steps of:
- (a) prompting the caller to speak the first character string beginning with a first character and ending with a last character thereof;
(b) generating speech feature data for each spoken character of the first character string;
(c) applying the speech feature data and voice recognition feature transformation data to a voice recognition feature transformation to generate a first set of parameters for each spoken character of the first character string, the first set of parameters for use in a voice recognition system;
(d) applying the speech feature data and voice verification feature transformation data to a voice verification feature transformation to generate a second set of parameters for each spoken character of the first character string, the second set of parameters for use in a voice verification system;
(e) recognizing the first character string using the first set of parameters;
(f) initially verifying the caller'"'"'s identify using the second set of parameters generated for the first character string; and
(g) repeating steps (a)-(c) and (e) using the second character string instead of the first character string to confirm the caller'"'"'s identity.
9 Assignments
0 Petitions
Accused Products
Abstract
The present invention describes a system and method for enabling a caller to obtain access to services via a telephone network by entering a spoken first character string having a plurality of digits. Preferably, the method includes the steps of prompting the caller to speak the first character string beginning with a first digit and ending with a last digit thereof, recognizing each spoken digit of the first character string using a speaker-independent voice recognition algorithm, and then following entry of the last digit of the first string, initially verifying the caller'"'"'s identity using a voice verification algorithm. After initial verification, the caller is again prompted to enter a second character string, which must also be recognized before access is effected.
203 Citations
5 Claims
-
1. A method for enabling a caller to obtain access to one or more services via a telephone network by speaking first and second character strings each having a plurality of characters, comprising the steps of:
-
(a) prompting the caller to speak the first character string beginning with a first character and ending with a last character thereof; (b) generating speech feature data for each spoken character of the first character string; (c) applying the speech feature data and voice recognition feature transformation data to a voice recognition feature transformation to generate a first set of parameters for each spoken character of the first character string, the first set of parameters for use in a voice recognition system; (d) applying the speech feature data and voice verification feature transformation data to a voice verification feature transformation to generate a second set of parameters for each spoken character of the first character string, the second set of parameters for use in a voice verification system; (e) recognizing the first character string using the first set of parameters; (f) initially verifying the caller'"'"'s identify using the second set of parameters generated for the first character string; and (g) repeating steps (a)-(c) and (e) using the second character string instead of the first character string to confirm the caller'"'"'s identity. - View Dependent Claims (2)
-
-
3. A method for enabling a caller to obtain access to one or more services via a telephone network by speaking first and second character strings each having one or more characters, comprising the steps of:
-
(a) prompting the caller to speak the first character string beginning with a first character and ending with a last character thereof; (b) generating speech feature data for each spoken character of the first character string; (c) applying the speech feature data of the first character string and voice recognition feature transformation data to a voice recognition feature transformation to generate a first set of parameters for each spoken character of the first character string, the first set of parameters for use in a voice recognition system; (d) applying the speech feature data and voice verification feature transformation data to a voice verification feature transformation to generate a second set of parameters for each spoken character of the first character string, the second set of parameters for use in a voice verification system; (e) recognizing the first character string using the first set of parameters of the first character string; (f) initially verifying the caller'"'"'s identify using the second set of parameters generated for the first character string; (g) prompting the caller to enter the second character string beginning with a first character and ending with a last character thereof; (h) generating speech feature data for each spoken character of the second character string; (i) applying the speech feature data of the second character string and voice recognition feature transformation data to a voice recognition feature transformation to generate a first set of parameters for each spoken character of the second character string, the first set of parameters of the second character string for use in a voice recognition system; and (j) recognizing the second character string using the first set of parameters of the second character string. - View Dependent Claims (4, 5)
-
Specification