US 2003/0125944 A1Published application

Method and system for identifying a user by voice

AssigneeCharles Schwab & Co., Inc.

InventorsROBERT C. WOHLSEN, SUE MCNEILL

Life of this patent

Estimating the term…

Loading patent…

Abstract

A method and apparatus identifies a caller as a user in a group of users. An enrollment process extracts a grammar of the user's password and a voiceprint of the user's password and name. A caller may identify himself as a user by speaking his name. The name is recognized and a number of users having a name most closely matching the name spoken is identified using voice recognition techniques. The caller then speaks his password and the grammar is identified that most closely matches the grammars of the passwords corresponding to the users identified from the spoken name. A voiceprint is extracted from the name and grammar spoken by the caller, and if the voiceprint matches the voiceprint extracted for the user identified using the grammar during that user's enrollment process, the caller is identified as that user.

Claims22

Dependent claims

A system for identifying a selected user from a first plurality of users, the system comprising:

a first grammar extractor having a first input operatively coupled to receive an identifier of one of the plurality of users, and a second input operatively coupled to receive a first utterance from the one of the first plurality of users uttered during a first session, the first grammar extractor for extracting a first grammar from the first utterance received at the first grammar extractor first input and for providing at an output the first grammar and the corresponding identifier received at the first input;
a grammar storage having an input/output coupled to the first grammar extractor output, for receiving the first grammar and identifier for each of the plurality of users and storing the grammar responsive to the identifier, and for providing at the input/output one of said grammars corresponding to an identifier responsive to receipt of said identifier at the grammar storage input/output;
a second grammar extractor having an input operatively coupled to receive a second utterance from the selected user uttered during a second session different from the first session, the second grammar extractor for extracting and providing at an output a second grammar responsive to the second utterance received at the second grammar extractor input;
and
a first recognizer having a first input coupled to the grammar storage input/output, and a second input-coupled to the second grammar extractor output, the first recognizer for identifying a match between a set of a plurality of the first grammars stored in the grammar storage and the second grammar received at the second first recognizer input, and for providing at an output coupled to an apparatus output, the identifier of the user corresponding to the grammar in the grammar storage most closely matching the grammar received at the first second input.

2 more elements

A computer program product comprising a computer useable medium having computer readable program code embodied therein for identifying a caller as a user of a computer system, the computer program product comprising:

computer readable program code devices configured to cause a computer to receive a first utterance;
computer readable program code devices configured to cause a computer to extract a grammar from the first utterance;
computer readable program code devices configured to cause a computer to compare the grammar extracted with a set of grammars, each grammar in the set of grammars corresponding to a user;
computer readable program code devices configured to cause a computer to, responsive to the computer readable program code devices configured to cause a computer to compare the grammar, identify a set of at least one user, the number of users in set of at least one user smaller than the number of users corresponding to the grammars in the set of grammars;
computer readable program code devices configured to cause a computer to extract a voiceprint from the first utterance;
computer readable program code devices configured to cause a computer to compare the voiceprint extracted with a voiceprint for each user in the set of at least one user;
and
computer readable program code devices configured to cause a computer to identify the user responsive to the comparing the voiceprint step.

5 more elements

Dependencies are inferred from the claim text.