System and method of speaker recognition

Patent metadata

Field	Value
Publication number	US-9418664-B2
Application number	US-201514603495-A
Country	US
Kind code	B2
Filing date	Jan 23, 2015
Priority date	Jun 19, 2012
Publication date	Aug 16, 2016
Grant date	Aug 16, 2016

Abstract

An authentication and authorization apparatus combines a unique identifier for a communications device with pre-stored voice recognition information. Incoming audio, associated with the unique identifier, is processed to authenticate the speaker. In response to successful authentication, a requested function or action embedded in the audio can be recognized and, if authorized, implemented by a displaced system.

First claim

The invention claimed is:

1. A method comprising:
a security system sensing a device identifier for a wireless communication device;
the security system receiving a digitized stream of incoming audio from the wireless communication device;
the security system requesting and receiving verbal password audio received by a microphone at the security system;
the security system selecting pre-stored voice related information associated with the device identifier;
the security system carrying out an authentication process by comparing the received verbal password audio to the selected pre-stored voice related information; and
the security system responding to authenticating the received verbal password audio by recognizing the incoming audio and implementing a function associated with the recognized incoming audio.

2. A method as in claim 1 which further comprising sensing signals using a near field communications reader.

3. A method as in claim 1 wherein the device identifier comprises one of a smart phone identifier, or a unique identifier of the wireless communication device.

4. A method as in claim 1 further comprising generating an output indicating that the verbal password audio has been authenticated.

5. A method as in claim 1 wherein, responsive to the recognized incoming audio, a command or request is transmitted to a remote location for implementation.

6. A method as in claim 1 further comprising providing a pre-stored database which contains voice recognition information for a plurality of individuals.

7. A method as in claim 6 further comprising receiving exemplary voice information, and identification information, and storing the exemplary voice information and the identification information in the pre-stored database for subsequent retrieval.

8. A speech authentication and authorization combination comprising:
circuitry to associate a device identifier for a communications device with pre-stored voice recognition information for an authorized user of the communications device;
circuitry to receive a stream of incoming audio from the communications device requesting that a function be implemented in a security system control panel;
microphone circuitry to receive verbal password audio at the security system control panel;
circuitry to carry out an authentication process by determining if at least part of the verbal password audio corresponds to the pre-stored voice recognition information associated with the device identifier;
circuitry to respond to results of the authentication process by implementing a speech recognition process relative to at least a portion of the stream of incoming audio; and
circuitry to implement the requested function.

9. A combination as in claim 8 further comprising circuitry, responsive to the speech recognition process, to generate a function designating output.

10. A combination as in claim 9 further comprising circuitry to transmit the function designating output to the security system control panel for implementation.

11. An apparatus as in claim 8 wherein the circuitry to associate includes a pre-stored data base of voice recognition information and associated communication device identification information.

12. An apparatus as in claim 8 further comprising the communications device, wherein the communications device includes a transmittable unique identifier, and wherein the circuitry to associate is located at one of, the communications device, and a displaced computer.

13. An apparatus as in claim 12 wherein the circuitry to carry out the authentication process is located at the displaced computer.

14. A method comprising:
providing a communication device having a device identifier;
establishing a data base having identification indicia linked to voice recognition information for each member of a plurality of persons;
receiving a stream of audio from the communication device;
receiving verbal password audio from a microphone associated with a security control panel;
associating the device identifier with the verbal password audio;
forwarding the device identifier and a representation of the verbal password audio to the data base;
retrieving selected voice recognition information from the data base, using the device identifier;
carrying out voice recognition processing between the retrieved voice recognition information, and the representation of the verbal password audio;
responsive to results of the voice recognition processing, determining if the retrieved voice recognition information and the representation of the verbal password audio correspond to a same person; and
carrying out speech recognition processing of a representation of the stream of audio.

15. A method as in claim 14 which further comprising issuing a request or instruction associated with the stream of audio to a displaced apparatus for implementation.

Assignees

• Honeywell Int Inc

Inventors

• Addy Kenneth L
• Rothman Ronald K

Classifications

• H04W12/06 Primary

  Authentication · CPC title

• G10L17/22 Primary

  Interactive procedures; Man-machine interfaces · CPC title

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L17/00

  Speaker identification or verification techniques · CPC title

• H04W12/71

  Hardware identity · CPC title