Meeting speech biasing and/or document generation based on meeting content and/or related data

Patent metadata

Field	Value
Publication number	US-12199783-B2
Application number	US-202217678657-A
Country	US
Kind code	B2
Filing date	Feb 23, 2022
Priority date	Feb 18, 2022
Publication date	Jan 14, 2025
Grant date	Jan 14, 2025

Abstract

Implementations relate to an application that can bias automatic speech recognition for meetings using data that may be associated with the meeting and/or meeting participants. A transcription of inputs provided during a meeting can additionally and/or alternatively be processed to determine whether the inputs should be incorporated into a meeting document, which can provide a summary for the meeting. In some instances, entries into a meeting document can be designated as action items, and those action items can optionally have conditions for reminding meeting participants about the action items and/or for determining whether an action item has been fulfilled. In this way, various tasks that may typically be manually performed by meeting participants, such as creating a meeting summary, can be automated in a more accurate manner. This can preserve resources that may otherwise be wasted during video conferences, in-person meetings, and/or other gatherings.

First claim

We claim:

1. A method implemented by one or more processors, the method comprising:
determining, at a computing device and by an application, that a meeting of multiple different participants is occurring, or is scheduled to occur,
wherein the meeting provides an opportunity for one or more participants of the multiple different participants to communicate information to other participants of the multiple different participants;

determining, by the application, that one or more instances of data are relevant to the meeting, at least based on the one or more instances of data comprising content that is determined to be associated with at least one participant of the multiple different participants, wherein determining that one or more instances of data are relevant to the meeting includes:
determining that one or more documents, comprising the content, were accessed by at least one participant of the multiple different participants within a threshold duration of time before the meeting;

causing, during the meeting of the multiple different participants, automatic speech recognition, performed on audio data, to be biased according to the content of the one or more instances of data, including causing the automatic speech recognition to be biased according to the content of the one or more documents determined to be accessed by the at least one participant within the threshold duration of time before the meeting,
wherein the audio data embodies speech from the one or more participants communicating the information to the other participants; and

generating, by the application, an entry for a meeting document based on speech recognition results from the automatic speech recognition biased according to the content of the one or more instances of data,
wherein the entry characterizes at least a portion of the information communicated from the one or more participants to the other participants.

2. The method of claim 1 , wherein determining that the one or more instances of data are relevant to the meeting further includes:
determining that the one or more instances of data include a document that has edited by at least one participant of the multiple different participants prior to the meeting.

3. The method of claim 1 , wherein determining that the one or more instances of data are relevant to the meeting further includes:
determining that the one or more instances of data include a document that has edited by at least one participant of the multiple different participants within the threshold duration of time prior to the meeting.

4. The method of claim 1 , wherein determining that the one or more instances of data are relevant to the meeting further includes:
determining that the one or more instances of data include a document that is being accessed and/or edited by at least one participant of the multiple different participants during the meeting.

5. The method of claim 1 , wherein determining that the one or more instances of data are relevant to the meeting further includes:
determining that the one or more instances of data include a document that embodies one or more terms identified in a meeting invitation for the meeting, and that is accessible to at least one participant of the multiple different participants.

6. The method of claim 1 , wherein determining that the one or more instances of data are relevant to the meeting further includes:
determining that the one or more instances of data include a document that embodies one or more terms identified in a title of a meeting invitation for the meeting.

7. The method of claim 1 , wherein causing the automatic speech recognition to be biased according to the content of the one or more instances of data includes:
generating, based on a portion of the audio data, one or more candidate terms for including with the entry in the meeting document; and
assigning a weight value to each term of the one or more candidate terms,
wherein each weight value is at least partially based on whether a particular term of the one or more candidate terms is included in the content of the one or more instances of data.

8. The method of claim 1 , wherein the threshold duration of time is determined based on when a meeting invitation was received and/or accessed by at least one participant who accessed the one or more documents.

9. The method of claim 1 , wherein determining that the one or more instances of data are relevant to the meeting further includes:
selecting one or more terms from the one or more documents as content that provides a basis for biasing the automatic speech recognition,
wherein the one or more terms are selected based on an inverse document frequency of the one or more terms appearing in the one or more documents.

10. A system comprising:
memory storing instructions;
one or more processors operable to execute the instructions to:
method implemented by one or more processors, the method comprising:
determine that a meeting of multiple different participants is occurring, or is scheduled to occur,
wherein the meeting provides an opportunity for one or more participants of the multiple different participants to communicate information to other participants of the multiple different participants;

determine that one or more instances of data are relevant to the meeting, at least based on the one or more instances of data comprising content that is determined to be associated with at least one participant of the multiple different participants, wherein in determining that one or more instances of data are relevant to the meeting one or more of the processors are to:
determine that one or more documents were accessed by at least one participant of the multiple different participants within a threshold duration of time before the meeting;

cause, during the meeting of the multiple different participants, automatic speech recognition, performed on audio data, to be biased according to the content of the one or more instances of data, including to cause the automatic speech recognition to be biased according to the content of the one or more documents determined to be accessed by the at least one participant within the threshold duration of time before the meeting,
wherein the audio data embodies speech from the one or more participants communicating the information to the other participants; and

generate an entry for a meeting document based on speech recognition results from the automatic speech recognition biased according to the content of the one or more instances of data,
wherein the entry characterizes at least a portion of the information communicated from the one or more participants to the other participants.

11. The system of claim 10 , wherein in determining that the one or more instances of data are relevant to the meeting one or more of the processors are further to:
determine that the one or more instances of data include a document that has been edited by at least one participant of the multiple different participants prior to the meeting.

12. The system of claim 10 , wherein in determining that the one or more instances of data are relevant to the meeting one or more of the processors are further to:
determine that the one or more instances of data include a document that has edited by at least one participant of the multiple different participants within a threshold duration of time prior to the meeting.

13. The system of claim 10 , wherein in determining that the one or more instances of data are relevant to the meeting one or more of the processors are further to:
determine that the one or more instances of data include a document that is being

Assignees

• Google Llc

Inventors

• Siohan Olivier
• MAKINO Takaki
• Maynez Joshua
• Mcdonald Ryan
• Shaparenko Benyah
• Nelson Joseph
• Sachdeva Kishan
• Garcia Basilio

Classifications

• G06F40/279

  Recognition of textual entities · CPC title

• H04L12/1831

  Tracking arrangements for later retrieval, e.g. recording contents, participants activities or behavior, network status · CPC title

• G10L15/1815

  Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning · CPC title

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L2015/228

  of application context · CPC title