Apparatus and method for speaker identification during telecommunication calls

• US 7,783,022 B1
• Filed: 04/09/2004
• Issued: 08/24/2010
• Est. Priority Date: 04/09/2004
• Status: Active Grant

• Current Assignee: Arlington Technologies, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Avaya Incorporated
• Inventors: Jay, Dylan, Lenard, Rohan
• Primary Examiner(s): Matar; Ahmad F
• Assistant Examiner(s): GAY, SONIA L
• Application Number:
  US10/821,725
• Time in Patent Office: 2,328 Days
• Field of Search: 379/202.01, 379351-356, 370/260, 370/261, 370/263, 370/264, 370/265, 370/266, 370/271, 370/352, 704/270, 704/231, 381/81
• US Class Current: 379/202.01
• 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: H04Q 2213/13095 PIN / Access code, authentication
• CPC Class Codes: H04Q 2213/13103 Memory
• CPC Class Codes: H04Q 2213/13204 Protocols
• CPC Class Codes: H04Q 2213/1324 Conference call
• CPC Class Codes: H04Q 2213/13378 Speech recognition, speech analysis
• CPC Class Codes: H04Q 2213/13389 LAN, internet
• CPC Class Codes: H04Q 3/72 Finding out and indicating number of calling subscriber

Abstract

An apparatus and method utilize information gathered by the telecommunication terminals that are part of the telecommunication conference to assist in the identification of the speaker at any point in time during a telecommunication conference.

Claims

1. A method for performing participant identification in a conference of a plurality of participants, comprising the steps of:

performing a simple speech algorithm to detect a change in an active participant among a set of the plurality of participants using an endpoint telecommunication unit by the endpoint telecommunication unit whereby the speech algorithm only determines the change in the active participant and not the identity of the active participant;

signaling the detected change to a system controller that is providing overall control of a telecommunication switching system which comprises the endpoint telecommunication unit and a conference unit by the endpoint telecommunication unit by transmission of a message whereby the conference unit is combining the audio information from the plurality of participants;

transmitting another message by the system controller to the conference unit by the system controller to inform the conference unit of the detected change; and

determining in response to the other message the identity of a new active participant of the set of the plurality of participants by the conference unit performing voice recognition to identify the new active participant in response to the signaled change whereby the conference unit processes speech information from only the endpoint telecommunication unit.

2. The method of claim 1 wherein the endpoint telecommunication unit is a telecommunication terminal.

3. The method of claim 1 wherein the endpoint telecommunication unit is a remote switch connecting a telecommunication terminal used by a subset of the set of the plurality of participants to the conference unit.

4. The method of claim 1 wherein the step of detecting comprises determining a use of a speakerphone on the endpoint telecommunication unit.

5. A system for providing a conference, comprising:

a conference unit which is combining the audio information from the plurality of participants of the conference;

a system controller that is providing overall control of a telecommunication switching system which comprises the conference unit and a plurality of endpoint telecommunication units;

system controller establishing the conference for a set of participants using a plurality of endpoint telecommunication units;

one of the plurality of endpoint telecommunication units providing service for a subset of the set of the plurality of participants, performing a simple speech algorithm to detect a change in a new active participant of the subset of the set of the plurality of participants whereby the speech algorithm only determines the change in the active participant and not the identity of the active participant and signaling the change to the system controller by transmission of a message;

system controller responsive to the signaled change to request the conference unit identify the new active participant of the subset of the set of the plurality of participants; and

the conference unit identifying the new active participant by performing voice recognition to identify the new active participant and signaling the identity to the system controller.

6. The system of claim 5 wherein the one of the plurality of endpoint telecommunication units is a telecommunication terminal.

7. The system of claim 5 wherein the one of the endpoint telecommunication units is a remote switch connecting a telecommunication terminal used by a subset of the set of the plurality of participants to the conference unit.

8. A non-transitory computer-readable medium comprising computer-executable instructions which, when executed by a processor, perform the steps of:

performing a simple speech algorithm to detect a change in an active participant among a set of the plurality of participants using an endpoint telecommunication unit by the endpoint telecommunication unit whereby the speech algorithm only determines the change in the active participant and not the identity of the active participant;

signaling the detected change to a system controller that is providing overall control of a telecommunication switching system which comprises the endpoint telecommunication unit and a conference unit by the endpoint telecommunication unit by transmission of a message whereby the conference unit is combining the audio information from the plurality of participants of the conference;

transmitting another message by the system controller to the conference unit to inform the conference unit of the detected change; and

determining in response to the other message the identity of a new active participant of the set of the plurality of participants by the conference unit performing voice recognition to identify the new active participant in response to the signaled change whereby the conference unit processes speech information from only the endpoint telecommunication unit.

9. The non-transitory computer-readable medium of claim 8 wherein the endpoint telecommunication unit is a telecommunication terminal.

10. The non-transitory computer-readable medium of claim 8 wherein the endpoint telecommunication unit is a remote switch connecting a telecommunication terminal used by the set of the plurality of participants to the conference unit.

11. The non-transitory computer-readable medium of claim 8 wherein the endpoint telecommunication unit is a speakerphone on the endpoint telecommunication unit.