Facilitation of a conference call

• US 7,539,290 B2
• Filed: 05/13/2005
• Issued: 05/26/2009
• Est. Priority Date: 11/08/2002
• Status: Active Grant

• Current Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Original Assignee: Verizon Services Corporation (Verizon Communications Inc.)
• Inventors: Ortel, William Charles Gormley
• Primary Examiner(s): Anwah; Olisa
• Application Number:
  US11/129,253
• Publication Number:
  US 20050207554A1
• Time in Patent Office: 1,474 Days
• Field of Search: 379/88.01, 379/158, 379/202.01, 379/201.02, 379/88.02
• US Class Current: 379/88.02
• CPC Class Codes: H04M 2201/38 Displays
• CPC Class Codes: H04M 2201/41 using speaker recognition speaker recognition per se G10L17/00
• CPC Class Codes: H04M 3/56 Arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities video conference systems H04N7/15
• CPC Class Codes: H04M 3/567 Multimedia conference systems

Abstract

There is provided a system for facilitating a conference call. The system includes a module to generate a real-time voiceprint from a voice input of a participant in the conference call, and a module to provide information indicative of the participant based on the real-time voiceprint.

Claims

1. A method, comprising:

participating in a communication between a first party at a first location and a second party at a second location, the first location remote from the second location and connected to the second location via a network;

receiving an audio signal during the communication at the first location,

generating a current voiceprint from the audio signal at the first location;

comparing the current voiceprint at the first location to at least one stored voiceprint;

identifying a matching voice print of the at least one stored voiceprint as a result of the comparing;

displaying an indication that the second party is speaking during the communication when the matching voiceprint is associated with the second party; and

retrieving the matching voiceprint from a database and storing the matching voiceprint at the first location;

wherein the at least one stored voiceprint is stored in the database which is remote from the first location.

2. The method of claim 1, further comprising:

refining the matching voiceprint during the communication using voice data from the second party received in the audio signal.

3. The method of claim 1, further comprising:

retrieving the at least one stored voiceprint from a database containing a plurality of voiceprints that include the at least one stored voiceprint;

displaying identifying information corresponding to the at least one stored voiceprint at the first location during the communication, the identifying information including an identity of the second party.

4. The method of claim 1, wherein the communication includes a third party at a third location, the third location remote from the first location and second location, and connected to the first location and second location via the network;

and further comprising;

displaying an indication that the third party is speaking during the communication when the matching voiceprint is associated with the third party.

5. The method of claim 4, further comprising:

retrieving the at least one stored voiceprint from a database containing a plurality of voiceprints;

displaying identifying information corresponding to the at least one stored voiceprint at the first location during the communication, the identifying information identifying the second party and the third party.

6. The method of claim 5, further comprising

recording at least a portion of the identifying information in a log;

recording notations indicating when one of the first party, second party and third party are speaking in the log during the communication, the notations generated as a result of identifying the matching voiceprint.

7. A machine-readable medium storing instructions executable by a processor and configured to cause the processor to perform the method of claim 1.

8. A machine-readable medium storing instructions executable by a processor and configured to cause the processor to perform the method of claim 4.

9. A system comprising:

a generator module that generates a first real-time voiceprint from an audio input of a conference call having two or more participants; and

a matching module that receives the first real-time voiceprint, compares the first real-time voiceprint to a number of previously stored reference voiceprints to determine a first matching voiceprint when said first real-time voiceprint best matches the first matching voiceprint, and automatically refines the first matching voiceprint during the conference call after the first matching voiceprint has been determined;

wherein the generator module further generates a second real-time voiceprint from the audio input of the conference call at a time later than the first real-time voiceprint, and the matching module further compares the second real-time voiceprint to the number of previously stored reference voiceprints to determine a second matching voiceprint when said second real-time voiceprint best matches the second matching voiceprint, said second real-time voiceprint comparison concurrent with the refining of the first matching voiceprint.

10. The system of claim 9, further comprising:

a module that displays information indicative of one of the two or more participants based on the first matching voiceprint.

11. The system of claim 10, wherein said information causes a display to show a representation of said one of the two or more participants.

12. The system of claim 9, further comprising:

a module that stores said reference voiceprint to a memory that is utilized by the matching module.

13. The system of claim 12, wherein said module that stores said reference voiceprint obtains said reference voiceprint from a library of reference voiceprints.