Name recognition of virtual meeting participants

• US 8,781,841 B1
• Filed: 06/07/2011
• Issued: 07/15/2014
• Est. Priority Date: 06/07/2011
• Status: Active Grant

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Wang, Zhuang
• Primary Examiner(s): Abebe, Daniel D
• Application Number:
  US13/155,250
• Time in Patent Office: 1,134 Days
• Field of Search: 704/275, 379/88.02, 379/205.01
• US Class Current: 704/275
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/225 Feedback of the input speech
• CPC Class Codes: H04M 2201/41 using speaker recognition
• CPC Class Codes: H04M 2201/42 Graphical user interfaces
• CPC Class Codes: H04M 2203/5054 Meet-me conference, i.e. participants dial-in
• CPC Class Codes: H04M 2203/5081 Inform conference party of participants, e.g. of change of participants
• 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

An example method is provided that may include receiving a first request to join a communication session; receiving voice data from a telephonic device in response to an audio prompt requesting a voice input from a dial-in user; interpreting the voice data to identify a particular name; and presenting the particular name in a graphical user interface associated with the communication session, the presentation of the particular name identifying that the dial-in user has joined the communication session.

Claims

1. A computer-implemented method comprising:

receiving a first request of a dial-in user to join a communication session from a telephonic device;

presenting the dial-in user with an option to opt-out of presenting voice data for use in identifying a name associated with the dial-in user;

if the dial-in user does not opt-out of presenting voice data, receiving voice data from the telephonic device in response to an audio prompt requesting a voice input from the dial-in user;

interpreting the voice data to identify a particular name associated with the dial-in user; and

presenting the particular name in a graphical user interface associated with the communication session, the presentation of the particular name identifying that the dial-in user has joined the communication session.

2. The method of claim 1, wherein the particular name is presented in a listing of meeting participant names, the listing including a plurality of names corresponding to a plurality of meeting participants identified as participating in the communication session.

3. The method of claim 2, further comprising:

identifying first voice data received from a first device associated with a first one of the plurality of meeting participants;

audibly presenting the first voice data within the communication session to other meeting participants in the plurality of meeting participants;

graphically presenting a first graphical effect associated with a presented listing of a first name in the listing of participant names, the first name corresponding to the first participant, wherein the graphical effect indicates that the first participant is speaking within the communication session;

identifying second voice data received from a second device associated with a second one of the plurality of meeting participants;

audibly presenting the second voice data within the communication session;

graphically presenting a second graphical effect associated with a presented listing of a second name in the listing of participant names, the second name corresponding to the second participant, wherein the second graphical effect indicates that the second participant is speaking within the communication session.

4. The method of claim 3, further comprising recording the communication session including voice data and video data presented during the communication session, the video data corresponding to presentation of the graphical user interface during the communication session and including the first and second graphical effects.

5. The method of claim 1, wherein interpreting the voice data includes speech recognition of the voice data to identify the particular name as spoken by the dial-in user.

6. The method of claim 5, further comprising:

audibly presenting the identified particular name to the dial-in user in response to interpreting the voice data, the presentation of the identified particular name including an audio prompt requesting the dial-in user to confirm that the particular name is the name of the dial-in user.

7. The method of claim 1, wherein interpreting the voice data includes:

performing voice recognition on the voice data to identify a particular voice profile from the voice data;

identifying that the particular voice profile substantially matches a particular voice signature of a particular user account in a set of user accounts, each user account in the set of user accounts including a corresponding voice signature; and

identifying that the particular name is associated with the particular user account.

8. The method of claim 7, further comprising:

identifying an invitation list associated with the communication session, the invitation list including a plurality of invitees;

identifying one or more user accounts associated with one or more of the plurality of invitees, wherein the set of user accounts includes the identified one or more user accounts associated with one or more of the plurality of invitees.

9. The method of claim 7, further comprising:

receiving second voice data from a second dial-in user;

performing voice recognition on the second voice data to identify a second voice profile from the second voice data;

determining that the second voice data does not match any voice signature included in the set of user accounts.

10. The method of claim 9, further comprising:

prompting the second dial-in user to speak a name associated with the second dial-in user; and

perform speech recognition on voice data received from the second dial-in user in response to the prompting of the second dial-in user, to generate a predicted name of the second dial-in user.

11. The method of claim 7, further comprising:

identifying a telephone number associated with the telephonic device;

identifying the set of user accounts from a plurality of user accounts, based at least in part on a comparison of the identified telephone number with telephone data included in the plurality of user accounts.

12. The method of claim 1, further comprising:

presenting to a second dial-in user the option to opt-out of presenting voice data for use in identifying a name associated with the second dial-in user;

receiving, from the second dial-in user, data accepting the option to opt-out; and

presenting, in the graphical user interface, a substantially generic identifier as corresponding to the second dial-in user, the substantially generic identifier identifying that the second dial-in user has joined the communication session.

13. The method of claim 1, wherein the voice data is first voice data and the dial-in user is a first dial-in user, the method further comprising:

receiving second voice data from the telephonic device;

determining that the second voice data corresponds to a second dial-in user using the telephonic device, wherein the second dial-in user is a user other than the first dial-in user;

interpreting the second voice data to identify a second name; and

presenting the second name in the graphical user interface.

14. The method of claim 13 further comprising:

receiving from the telephonic device additional voice data during the communication session;

performing voice recognition on the additional voice data to identify that the additional voice data corresponds to speaking by the second dial-in user.

15. A system comprising:

a memory element configured for storing data;

a processor operable to execute instructions associated with the data;

a virtual meeting server configured to facilitate a virtual meeting session over a network to a plurality of communication devices;

a name recognition engine configured to interact with the processor such that the system is configured for;

receiving a first request of a dial-in user to join a communication session from a telephonic device;

presenting to the dial-in user with an option to opt-out of presenting voice data for use in identifying a name associated with the dial-in user;

if the dial-in user does not opt-out of presenting voice data, receiving voice data from the telephonic device in response to an audio prompt requesting a voice input from the dial-in user;

interpreting the voice data to identify a particular name associated with the dial-in user; and

presenting the particular name in a graphical user interface associated with the communication session, the presentation of the particular name identifying that the dial-in user has joined the communication session.

16. The system of claim 15, further comprising a GUI engine configured to:

present a listing of meeting participant names in a graphic portion of the virtual meeting session, the listing of meeting participant names including a plurality of participant names, each participant name corresponding to a respective user of at least one communication; and

present a graphical effect associated with a particular participant name of a particular user of a particular communication device included in the listing in response to voice data being received from the particular communication device.

17. The system of claim 15, wherein the name recognition engine is further configured to:

perform voice recognition on the received voice data to compare the received voice data to a set of voice signatures, each voice signature in the set of voice signatures associated with a respective person name in a plurality of person names; and

associate the received voice data with a particular person name in the plurality of person names based on a determination that the received voice data at least partially matches a particular voice signature in the set of voice signatures associated with the particular person name.

18. The system of claim 17, wherein the data stored by the memory element includes the set of voice signatures and records corresponding to the plurality of person names.

19. The system of claim 15, wherein the name recognition engine is further configured to perform speech recognition on the received voice data to identify the particular name as spoken by a particular user.

20. The system of claim 15, wherein the name recognition engine is further configured for:

presenting to a second dial-in user the option to opt-out of presenting voice data for use in identifying a name associated with the second dial-in user;

receiving, from the second dial-in user, data accepting the option to opt-out;

presenting, in the graphical user interface, a substantially generic identifier as corresponding to the second dial-in user, the substantially generic identifier identifying that the second dial-in user has joined the communication session.