System, method and computer-readable medium for verbal control of a conference call

• US 8,380,521 B1
• Filed: 09/27/2011
• Issued: 02/19/2013
• Est. Priority Date: 07/17/2007
• Status: Active Grant

• Current Assignee: West Technology Group LLC (West Corporation)
• Original Assignee: West Corporation
• Inventors: Maganti, Srinivas, Sojka, Myron P.
• Primary Examiner(s): Lerner, Martin
• Application Number:
  US13/246,092
• Time in Patent Office: 511 Days
• Field of Search: 704/246, 704/251, 704/270, 704/270.1, 704/275, 379/88.01, 379/93.02, 379/158, 379/202.01, 379/204.01, 370/260, 370/261
• US Class Current: 704/275
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: H04L 12/1827 Network arrangements for conference optimisation or adaptation
• CPC Class Codes: H04L 65/403 Arrangements for multi-party communication, e.g. for conferences data switching systems for conference H04L12/18; arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities H04M3/56; television conferencing systems H04N7/15

Abstract

A system, method, and computer readable medium that facilitate verbal control of conference call features are provided. Automatic speech recognition functionality is deployed in a conferencing platform. Hot words are configured in the conference platform that may be identified in speech supplied to a conference call. Upon recognition of a hot word, a corresponding feature may be invoked. A speaker may be identified using speaker identification technologies. Identification of the speaker may be utilized to fulfill the speaker'"'"'s request in response to recognition of a hot word and the speaker. Particular participants may be provided with conference control privileges that are not provided to other participants. Upon recognition of a hot word, the speaker may be identified to determine if the speaker is authorized to invoke the conference feature associated with the hot word.

Claims

1. A method, comprising:

evaluating a conference stream, in a conferencing system, with a speech recognition algorithm;

determining if a first hot word is identified in the conference stream, wherein at least a caller name is used to populate a voice template for identifying the first hot word;

responsive to determining the first hot word is in the conference stream, invoking a conference feature associated with the first hot word; and

suppressing the first hot word in the stream prior to transmission of the stream to conference participants.

2. The method of claim 1, comprising bridging a plurality of conference call legs to form the conference stream.

3. The method of claim 1, comprising:

determining a second hot word is identified in the conference stream; and

invoking a speaker recognition algorithm to identify the speaker of the second hot word, wherein a speech recognition algorithm and the speaker recognition algorithm are at least one of a same algorithm or a different algorithm.

4. The method of claim 3, comprising determining if the speaker is authorized to invoke a conference feature associated with the second hot word.

5. The method of claim 4, comprising invoking the conference feature associated with the second hot word in response to determining the speaker is authorized.

6. The method of claim 4, wherein determining if the speaker is authorized comprises evaluating a record assigned to the speaker that specifies privileges allocated to the speaker.

7. The method of claim 1, wherein determining if a first hot word is identified in the conference stream comprises comparing a word identified in the conference stream with a database of hot words configured for the conferencing system.

8. A computer-readable medium having computer-executable instructions for execution by a processing system, the computer-readable medium comprising instructions for:

evaluating a conference stream with a speech recognition algorithm;

determining if a hot word is identified in the conference stream, wherein at least a caller name is used to populate a voice template for identifying the hot word;

responsive to determining the hot word is in the conference stream, identifying a speaker of the hot word; and

suppressing the hot word in the stream prior to transmission of the stream to conference participants.

9. The computer-readable medium of claim 8, comprising bridging a plurality of conference call legs to form the conference stream.

10. The computer-readable medium of claim 8, comprising instructions for determining whether the speaker is authorized to invoke a conference feature associated with the hot word.

11. The computer-readable medium of claim 10, comprising instructions for invoking the conference feature in response to determining the speaker is authorized to invoke the conference feature.

12. The computer-readable medium of claim 10, wherein the conference feature is not invoked in response to determining the speaker is not authorized to invoke the conference feature.

13. The computer-readable medium of claim 8, comprising instructions that define conference privileges of each participant of the conference call.

14. The computer-readable medium of claim 8, comprising instructions for:

determining if a participant'"'"'s name was spoken in a pre-defined interval subsequent to the hot word; and

invoking a conference feature associated with the hot word on behalf of a participant having the participant'"'"'s name.

15. The computer-readable medium of claim 8, wherein the instructions for determining if the hot word is identified in the conference stream comprises instructions for comparing a word identified in the conference stream with a database of hot words configured for the conferencing system.

16. A system, comprising:

a database that specifies privileges of respective conference participants;

a media server adapted to terminate a conference leg with each of a plurality of terminal devices of the participants, evaluate a conference stream with a speech recognition algorithm, determine a hot word is included in the conference stream, and identify a speaker of the hot word, wherein the hot word is associated with a conference feature, wherein the media server suppresses the hot word in the conference stream prior to transmission of the conference stream to the conference participants, wherein at least a caller name is used to populate a voice template for identifying the hot word; and

an application server communicatively coupled with the media server and adapted to provide control information to the media server for managing the conference call, wherein the application server is notified of the hot word and the speaker, and wherein the application server interrogates the database to determine if the speaker is authorized to invoke the conference feature.

17. The system of claim 16, wherein the media server is adapted to bridge a plurality of conference legs to form the conference stream.

18. The system of claim 16, wherein the application server determines the speaker is authorized to invoke the conference feature.

19. The system of claim 18, wherein the application server directs the media server to invoke the conference feature.

20. The system of claim 16, comprising a database of hot words that is communicatively coupled with the media server, wherein the media server determines the hot word is included in the conference stream by obtaining a match with the hot word and an entry in the database of hot words.