Automated camera aiming for identified talkers

• US 6,192,342 B1
• Filed: 11/17/1998
• Issued: 02/20/2001
• Est. Priority Date: 11/17/1998
• Status: Expired due to Term

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Vtel Corporation
• Inventors: Akst, Adam
• Primary Examiner(s): {haeck over (S)}mits, T{overscore (a)}livaldis I.
• Assistant Examiner(s): Nolan, Daniel A.
• Application Number:
  US09/193,828
• Time in Patent Office: 826 Days
• Field of Search: 704/270, 704/275, 379/93.14, 379/93.21, 380/257, 713/153, 348/15, 348/211, 348/17, 348/213
• US Class Current: 704/275
• CPC Class Codes: H04N 7/142 Constructional details of the terminal equipment, e.g. arrangements of the camera and the display
• CPC Class Codes: H04N 7/147 Communication arrangements, e.g. identifying the communication as a video-communication, intermediate storage of the signals selecting H04Q

Abstract

A camera is targeted using voice recognition analysis. Audio information is received by a talker identification (TID) module from a microphone. The TID module automatically performs a voice recognition analysis on the audio information to uniquely identify which of a plurality of talkers is talking. The camera is automatically controlled to target a camera preset location corresponding to the talker identified to be talking.

Claims

1. A method for targeting a camera, the method comprising:

receiving audio information by a talker identification (TID) module from a microphone;

automatically performing by the TID module a voice recognition analysis on the audio information to uniquely identify which of a plurality of talkers is talking by the voice pattern; and

automatically controlling the camera to target a camera preset location corresponding to said talker identified to be talking.

2. The method of claim 1, the method further comprising a plurality of initialization operations, the initialization operations comprising:

manually targeting a camera to a location of a talker;

saving camera preset information corresponding to the location of the talker after the camera is manually targeted to the talker;

using a microphone to obtain audio information regarding a voice of the talker;

saving TID information identifying the talker after obtaining the audio information, wherein the camera preset information and the TID information are saved to identify a talker/camera combination.

3. The method of claim 2 wherein

the camera is one of a plurality of cameras;

the method further includes manually targeting each camera to a location of a talker;

repeating the initialization operations for each camera so that camera preset information and TID information are saved to identify a talker/camera combination corresponding to each camera.

4. The method of claim 2, the method further comprising:

repeating the initialization operations for each talker of a plurality of talkers so that camera preset information and TID information are saved to identify each of a plurality of talker/camera combinations corresponding to each talker.

5. The method of claim 4 wherein

the automatically performing by the TID module a voice recognition analysis includes comparing the received audio information to the TID information to identify a talker corresponding to the received audio information;

and

the automatically controlling the camera to target a camera to the camera preset location includes targeting the camera to the location identified by the camera preset information which corresponds to the talker corresponding to the received audio information.

6. The method of claim 2 wherein the initialization operations further comprise:

repeating the initialization operations responsive to operator input.

7. The method of claim 2 further comprising:

confirming that the talker/camera combination has been saved.

8. An apparatus for targeting a camera, the apparatus comprising:

a camera targeting controller for automatically targeting a camera to one of a plurality of camera presets responsive to receiving audio information and identifying the audio information as corresponding to talker identification information which uniquely identifies a talker from a plurality of talkers by the voice pattern and which corresponds to the one of the camera presets.

9. The apparatus of claim 8 further comprising:

a computer-readable storage medium; and

wherein

the camera targeting controller is a software module store on the computer-readable storage medium.

10. The apparatus of claim 9 further comprising:

an information processing system, the information processing system including the computer-readable storage medium.

11. The apparatus of claim 10 wherein the information processing system is a general purpose personal computer system.

12. The apparatus of claim 10 wherein the information processing system is a videoconference system.

13. The apparatus of claim 8 wherein the apparatus is a videoconference system comprising:

a camera;

a microphone;

an information processing unit, the information processing unit comprising the camera targeting controller, the information processing unit being coupled to receive the audio information from the microphone, the information processing unit being coupled to receive camera preset information from the camera when the camera is initially targeted on a talker and audio information corresponding to the talker is initially received.

14. The apparatus of claim 8 wherein the camera targeting controller comprises:

a talker identification module, the talker identification module generating the talker identification information by performing a voice recognition analysis on the audio information responsive to receiving the audio information; and

a talker identification memory, the talker identification module storing the talker identification information corresponding to the received audio information responsive to receiving the talker identification information, the talker identification module storing camera preset information responsive to receiving the camera preset information, the camera preset information identifying a location to be targeted by the camera responsive to the talker identification module receiving talker identification information corresponding to the camera preset information.

15. A method for targeting a camera, the method comprising:

saving talker/camera combination information for at least one of a plurality of talker/camera combinations, the talker/camera combination information including talker identification information for identifying a talker by voice and camera preset information corresponding to the location of said talker identified by the voice pattern;

determining whether subsequent talker/camera combinations are to be saved;

saving subsequent talker camera combinations if subsequent talker/camera combinations are to be saved;

receiving first audio information;

recognizing a first talker by determining whether the first audio information corresponds to first talker identification information of the saved talker identification information;

determining first camera preset information corresponding to the first talker identification information;

targeting a camera preset location indicated by the first camera preset information.

16. The method of claim 15 further comprising:

manually targeting a camera on a talker;

determining the camera preset information corresponding to the talker after manually targeting the camera on the talker

recording a voice of the talker; and

generating the talker identification information by processing the voice of the talker to uniquely identify the talker by voice.

17. The method of claim 15 wherein

the recognizing the first talker by determining whether the first audio information corresponds to the first talker identification information includes automatically performing a voice recognition analysis on the first audio information to uniquely identify which of a plurality of talkers is talking.