Distributed device meeting initiation

Patent metadata

Field	Value
Publication number	US-11468895-B2
Application number	US-201916399152-A
Country	US
Kind code	B2
Filing date	Apr 30, 2019
Priority date	Apr 30, 2019
Publication date	Oct 11, 2022
Grant date	Oct 11, 2022

Abstract

A computer implemented method includes receiving audio streams at a meeting server from two distributed devices that are streaming audio captured during an ad-hoc meeting between at least two users, comparing the received audio streams to determine that the received audio streams are representative of sound from the ad-hoc meeting, generating a meeting instance to process the audio streams in response to the comparing determining that the audio streams are representative of sound from the ad-hoc meeting, and processing the received audio streams to generate a transcript of the ad-hoc meeting.

First claim

The invention claimed is:

1. A computer implemented method comprising:
receiving audio streams at a meeting server from two distributed devices that are streaming audio captured during an unplanned ad-hoc meeting between a plurality of users where no method has been set up to create a transcript of the ad-hoc meeting, the two distributed devices each comprising a mobile wireless device associated with a respective user in the ad-hoc meeting;
comparing the audio streams to recognize that an unplanned ad-hoc meeting is occurring and to determine that the audio streams are representative of sound from the ad-hoc meeting;
generating a meeting instance to process the audio streams in response to determining that the audio streams are representative of sound from the ad-hoc meeting;
processing the received audio streams via the meeting instance to generate a transcript of the ad-hoc meeting; and
providing the transcript to at least one of the mobile wireless devices associated with the users in the ad-hoc meeting.

2. The method of claim 1 wherein the received audio streams are compared by calculating the normalized cross correlation coefficients between two audio streams.

3. The method of claim 2 wherein the received audio streams are determined to be representative of sound from the ad-hoc meeting by comparing the normalized cross correlation coefficients to a selected threshold.

4. The method of claim 1 and further comprising authenticating the users prior to processing the audio streams to generate a transcript.

5. The method of claim 4 wherein authenticating the users comprises receiving a confirmation from a user that has already been authenticated for the meeting instance.

6. The method of claim 1 and further comprising adding an additional distributed device to the meeting instance based on receiving audio from the additional distributed device corresponding to the ad-hoc meeting.

7. The method of claim 1 and further comprising:
generating a meeting code corresponding to the meeting instance; and
adding a device providing the meeting code to the meeting instance.

8. The method of claim 1 wherein the sound from the ad-hoc meeting includes an audio watermark.

9. The method of claim 8 wherein the audio watermark comprises sound encoded with information representative of the ad-hoc meeting emitted by one of the distributed devices.

10. The method of claim 1 wherein at least two of the audio streams are provided by an ambient capture device having an array of microphones in fixed positions.

11. A machine-readable storage device having instructions for execution by a processor of a machine to cause the processor to perform operations to perform a method, the operations comprising:
receiving audio streams at a meeting server from two distributed devices that are streaming audio captured during an unplanned ad-hoc meeting between a plurality of users where no method has been set up to create a transcript of the ad-hoc meeting, the two distributed devices each comprising a mobile wireless device associated with a respective user in the ad-hoc meeting;
comparing the audio streams to recognize that an unplanned ad-hoc meeting is occurring and to determine that the audio streams are representative of sound from the ad-hoc meeting;
generating a meeting instance to process the audio streams in response to determining that the audio streams are representative of sound from the ad-hoc meeting;
processing the received audio streams via the meeting instance to generate a transcript of the ad-hoc meeting; and
providing the transcript to one of the mobile wireless devices associated with the users in the ad-hoc meeting.

12. The device of claim 11 wherein the received audio streams are compared by calculating the normalized cross correlation coefficients between two audio streams.

13. The device of claim 12 wherein the received audio streams are determined to be representative of sound from the ad-hoc meeting by comparing the normalized cross correlation coefficients to a selected threshold.

14. The device of claim 12 wherein in the operations further comprise adding an additional distributed device to the meeting instance based on receiving audio from the additional distributed device corresponding to the ad-hoc meeting.

15. The device of claim 12 wherein in the operations further comprise:
generating a meeting code corresponding to the meeting instance; and
adding a device providing the meeting code to the meeting instance.

16. A device comprising:
a processor; and
a memory device coupled to the processor and having a program stored thereon for execution by the processor to perform operations comprising:
receiving audio streams at a meeting server from two distributed devices that are streaming audio captured during an unplanned ad-hoc meeting between a plurality of users where no method has been set up to create a transcript of the ad-hoc meeting, the two distributed devices each comprising a mobile wireless device associated with a respective user in the ad-hoc meeting;
comparing the audio streams to recognize that an unplanned ad-hoc meeting is occurring and to determine that the audio streams are representative of sound from the ad-hoc meeting;
generating a meeting instance to process the audio streams in response to determining that the audio streams are representative of sound from the ad-hoc meeting;

processing the received audio streams via the meeting instance to generate a transcript of the ad-hoc meeting; and
providing the transcript to one of the mobile wireless devices associated with the users in the ad-hoc meeting.

17. The device of claim 16 wherein the received audio streams are compared by calculating the normalized cross correlation coefficients between two received audio streams, wherein the received audio streams are determined to be representative of sound from the ad-hoc meeting by comparing the normalized cross correlation coefficients to a selected threshold.

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Yoshioka Takuya
• Stolcke Andreas
• Chen Zhuo
• Dimitriadis Dimitrios Basile
• Zeng Nanshan
• Qin Lijuan
• Hinthorn William Isaac
• Huang Xuedong

Classifications

• H04R1/406

  microphones · CPC title

• G10L25/06

  the extracted parameters being correlation coefficients · CPC title

• G06Q10/10

  Office automation; Time management · CPC title

• G10L25/51

  for comparison or discrimination · CPC title

• G10L15/26 Primary

  Speech to text systems (G10L15/08 takes precedence) · CPC title