Speaker identification during telephone conferencing

• US 20050135583A1
• Filed: 12/18/2003
• Published: 06/23/2005
• Est. Priority Date: 12/18/2003
• Status: Active Grant

• Current Assignee: Dolby International AB (Dolby Laboratories Incorporated)
• Original Assignee: Electronic Data Systems Corporation (Perspecta, Inc.)
• Inventors: Kardos, Christopher P.
• Granted Patent: US 7,305,078 B2
• Time in Patent Office: Days
• US Class Current: 379/142.10
• CPC Class Codes: H04M 1/271 controlled by voice recognition
• CPC Class Codes: H04M 1/575 Means for retrieving and displaying personal data about calling party
• CPC Class Codes: H04M 2201/38 Displays
• CPC Class Codes: H04M 3/42042 Notifying the called party of information on the calling party details within substation equipment H04M1/57, signalling details H04Q3/72
• 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 3/569 using the instant speaker's algorithm speech detection per se G10L25/78

Abstract

Systems and techniqes for identifying a participant in a teleconference allow other participants at remote locations to be informed of the identify of a current speaker. A currently speaking participant is identified in a teleconference conducted using a connection on a circuit-switched network, and a signal indicating an identifier of the currently speaking participant is transmitted over the connection on the circuit-switched network. The signal is received, and the identifier of the currently speaking participant is displayed at a participating location. The displayed identifier is determined based on the indication in the signal.

Claims

1. A method for identifying a participant in a teleconference, the method comprising:

identifying a currently speaking participant in a teleconference conducted using a connection on a circuit-switched network;

transmitting a signal indicating an identifier of the currently speaking participant over the connection on the circuit-switched network;

receiving the signal at a participating location; and

displaying the identifier of the currently speaking participant at the participating location, with the displayed identifier being determined based on the indication in the signal.

2. The method of claim 1 further comprising:

identifying at least one participant in the teleconference;

storing an identifier of the at least one participant; and

transmitting the identifier of the participant to the participating location prior to transmitting the signal.

3. The method of claim 2 wherein identifying the at least one participant comprises reading a unique identifier for the at least one participant from a card.

4. The method of claim 2 wherein identifying the at least one participant comprises receiving a unique identifier entered with a keypad.

5. The method of claim 2 wherein identifying the at least one participant comprises recognizing a voice sample provided by the at least one participant.

6. The method of claim 2 further comprising:

storing a voiceprint for the at least one participant, wherein identifying the currently speaking participant comprises comparing speech from the currently speaking participant to the stored voiceprint.

7. The method of claim 1 further comprising:

receiving an identifier of a participant in the teleconference; and

storing the identifier in a list of participants.

8. The method of claim 1 wherein:

identifying the currently speaking participant comprises identifying a location of the participant; and

transmitting the signal including the identifier of the currently speaking participant comprises transmitting an identifier of the location.

9. The method of claim 1 further comprising:

receiving a signal including an indication of an identifier of a currently speaking participant in the teleconference;

accessing the identifier using the indication; and

displaying the accessed identifier of the speaking participant.

10. The method of claim 9 wherein accessing the identifier comprises accessing the identifier from a list of participants.

11. The method of claim 1 wherein identifying the currently speaking participant comprises:

comparing a live voice signal of the currently speaking participant to a set of stored voice signals;

identifying a stored voice signal from the set of stored voice signals that matches the live voice signal; and

accessing an indication of an identifier associated with the identified stored voice signal, wherein the indication is included in the transmitted signal.

12. The method of claim 1 wherein identifying the currently speaking participant comprises detecting an action performed by the currently speaking participant indicating that the currently speaking participant is speaking.

13. The method of claim 12 wherein the action includes pressing a button.

14. The method of claim 1 wherein identifying the currently speaking participant comprises:

detecting a period of uninterrupted speech by the participant.

15. The method of claim 1 further comprising:

detecting a period of silence from the participant;

determining that the participant has stopped speaking in response to the detected period of silence; and

transmitting a signal indicating that the participant has stopped speaking.

16. The method of claim 15 further comprising:

receiving a signal indicating that the participant has stopped speaking; and

removing the identifier of the participant from a display in response to the received signal indicating that the participant has stopped speaking.

17. The method of claim 1 wherein the signal is received by a central controller.

18. The method of claim 1 wherein the signal is received at the participating location.

19. A system for identifying a speaker participating in a conference call, the system comprising:

a voice recognition module operable to identify a speaking participant in a teleconference; and

a communications module operable to send a signal indicating the speaking participant, wherein;

the teleconference occurs over a circuit-switched connection, and

the signal is sent over the same circuit-switched connection used for voice communications in the teleconference.

20. The system of claim 19 further comprising a display operable to display an identifier of at least one participant in the teleconference that is speaking.

21. The system of claim 19 further comprising a memory operable to store an identifier of the speaking participant, wherein the signal includes an indication of the stored identifier.

22. The system of claim 21 wherein:

the speaking participant is one of multiple participants at a participating location;

the memory stores identifiers of the multiple participants;

the communications module is operable to receive identifiers of participants at other locations to be stored by the memory; and

the communications module is operable to transmit the identifiers of the multiple participants.

23. The system of claim 21 wherein:

the memory is operable to store a voiceprint of at least one participant in the teleconference; and

the voice recognition module is operable to compare the stored voiceprint with a live voice signal from the speaking participant to determine if the participant corresponding to the stored voiceprint is speaking.

24. The system of claim 19 wherein the communications module is operable to receive a signal that an individual at another location is speaking, the system further comprising a display operable to display an identity of the location at which the individual is speaking.

25. The system of claim 19 further comprising a card reader operable to read information stored on a card that identifies the participant in the teleconference.

26. The system of claim 19 further comprising a keypad operable to receive a code that uniquely identifies the participant in the teleconference.

27. The system of claim 19 further comprising a button operable, when pressed to indicate to the voice recognition module that the participant is speaking.