Voice command control and verification system

• US 6,081,782 A
• Filed: 12/29/1993
• Issued: 06/27/2000
• Est. Priority Date: 12/29/1993
• Status: Expired due to Term

• Current Assignee: AT&T Corporation (AT&T, Inc.)
• Original Assignee: Lucent Technologies, Inc. (Nokia Corporation)
• Inventors: Rabin, Michael D.
• Primary Examiner(s): Hudspeth, David R.
• Assistant Examiner(s): ZINTEL, HAROLD ALBERT
• Application Number:
  US08/175,326
• Time in Patent Office: 2,372 Days
• Field of Search: 395/2.84, 395/2.82, 379/88, 379/89
• US Class Current: 704/275
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G07C 9/37 using biometric data, e.g. fingerprints, iris scans or voice recognition
• CPC Class Codes: G10L 15/06 Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice G10L15/14 takes precedence
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces

Abstract

A voice command control and verification system and method stores for each authorized user, one or a series of speech models of voice commands or phrases uttered by the authorized user. Each speech model has an associated action component which specifies the specific action that the authorized user desires in response to the issuance of the corresponding voice command. Each user has a means of asserting his or her claimed identity to the system, preferably without an overt action such as the entry of digits. When an identity is asserted, and a voice command is thereafter spoken by a person, the system first matches a model of the voice command against the stored models for the user having the claimed identity. If there is a match, so that the voice command can be uniquely interpreted as corresponding to its associated action component, the system then verifies the claimed identity of the user by comparing the vocal characteristics contained in the same command with the vocal characteristics of the stored model. Upon successful verification, the command is executed in accordance with the associated action component. The user of the system has thus issued only a single command to both operate the system and to verify his or her identity.

Claims

1. A method for executing voice commands for authorized users, comprising the steps of

storing, for each authorized user, at least one speech model associated with a voice command, said command having an associated action component;

receiving from a person claiming to be an authorized user, a claimed identity and a voice command;

comparing said received voice command to said at least one stored speech model for the authorized user having said claimed identity;

if said voice command matches said at least one stored speech model for said authorized user so that said voice command can be uniquely interpreted as corresponding to its associated action component, verifying said claimed identity of said person by further matching vocal characteristics of said voice command with said stored model; and

if said identity is verified, utilizing said associated action component to execute said voice command for said person using said system.

2. A system for responding to voice commands, said system comprising:

means for storing, for each user of said system, models of phrases representing commands in the voice of each user;

means for receiving a particular phrase representing a command from a person claiming to be a particular one of said users;

means for comparing said particular phrase with the models stored for said particular one of said users to identify said particular phrase;

means for verifying the identity of said particular one of said users by comparing said particular phrase with the model of the same phrase which was previously stored; and

means for performing a command associated with said particular phrase if said verification is positive.

3. A method for permitting a user to control a system with voice commands, comprising the steps of

receiving a command spoken by said user and a claimed identity of said user;

matching said command against stored models of phrases for said user having said claimed identity;

if there is a matched stored model, verifying said claimed identity of said user by comparing the spoken command with said matched stored model; and

upon successful verification, executing said command.

4. The invention defined in claim 3 wherein said executing step comprises

executing an action component associated with said command.

5. A voice controlled telecommunications system comprising:

means for assigning to each user a unique telephone number that the user dials to access the telecommunications network;

means for storing for each user, models of voice commands accessible by a speech recognition system and by a speaker verification system;

means for storing, for each of said commands, an associated destination telephone number;

means in said speech recognition system responsive to dialing of said unique telephone number and uttering of a voice command by a user, for performing speech recognition by matching said voice command with one of said stored models of voice commands for that user;

means in said speaker verification system responsive to said speech recognition means for verifying the identity of said user by comparing said voice command with the previously stored model of that voice command for the user; and

means responsive to verification of the identity of the user for executing said voice command by completing the call to the desired destination using said destination telephone number associated with said command.

6. A method of recognizing voice commands of authorized users of a system, the method comprising the steps of:

receiving a claim of identity from a person;

receiving an utterance of a system command from said person;

performing a speech recognition process on said utterance;

performing a speaker verification process on said utterance;

if said utterance is recognized as a command to said system and if said claimed identity is verified based on said utterance, providing a signal to said system indicating that a command has been presented by an authorized user for execution.

7. The method of claim 6 wherein said speech recognition process is performed with use of models of speech representing system commands.

8. The method of claim 7 wherein said speaker verification process is performed with use of at least one model of speech representing at least one command, said at least one model trained by the person whose identity is claimed.

9. The method of claim 8 further comprising the step of executing said recognized command.