Automated outline generation of captured meeting audio in a collaborative document context
A collaborative content management system allows multiple users to access and modify collaborative documents. When audio data is recorded by or uploaded to the system, the audio data may be transcribed or summarized to improve accessibility and user efficiency. Text transcriptions are associated with portions of the audio data representative of the text, and users can search the text transcription and access the portions of the audio data corresponding to search queries for playback. An outline can be automatically generated based on a text transcription of audio data and embedded as a modifiable object within a collaborative document. The system associates hot words with actions to modify the collaborative document upon identifying the hot words in the audio data. Collaborative content management systems can also generate custom lexicons for users based on documents associated with the user for use in transcribing audio data, ensuring that text transcription is more accurate.
1. A computer-implemented method comprising:
accessing, by a content creation system, captured audio data including speech of one or more speakers, the captured audio data associated with a document;
transcribing, by the content creation system, the captured audio data into text representative of the speech;
identifying, by the content creation system, a first portion of the text associated with a candidate document modification; and
modifying, by the content creation system, the document based on the candidate document modification associated with the identified first portion of the text to include at least a second portion of the text.
2. The computer-implemented method of claim 1 , wherein modifying the document comprises including, by the content creation system, the first portion of the text and including the second portion of the text within the document.
3. The computer-implemented method of claim 1 , wherein the first portion of the text includes one or more hot words, and wherein each hot word is associated with a document modification.
4. The computer-implemented method of claim 3 , wherein each hot word is pre-determined such that speaking a hot word triggers the modification of the document.
5. The computer-implemented method of claim 3 , wherein a hot word of the one or more hot words is associated with an action of an action item, and wherein modifying the document comprises including text within the document identifying an action item.
6. The computer-implemented method of claim 5 , wherein the text identifying the action item further identifies one or more people associated with the action item.
7. The computer-implemented method of claim 5 , wherein the text identifying the action item further identifies a due date associated with the action item.
8. The computer-implemented method of claim 3 , wherein a hot word of the one or more hot words is associated with a decision action, and wherein modifying the document comprises including text within the document identifying a decision made during the speech.
9. The computer-implemented method of claim 3 , wherein a hot word of the one or more hot words is associated with an assignment action, and wherein modifying the document comprises including text within the document identifying an assignment made during the speech.
10. The computer-implemented method of claim 9 , wherein the text identifying the assignment further identifies a task associated with the assignment.
11. The computer-implemented method of claim 10 , wherein modifying the document further comprises including a status indicator representative of a status of the task.
12. The computer-implemented method of claim 10 , wherein modifying the document further comprises tagging one or more users to whom the task is assigned within the document.
13. The computer-implemented method of claim 3 , wherein a hot word of the one or more hot words is associated with a tag action, and wherein modifying the document comprises tagging a user within the document.
14. The computer-implemented method of claim 3 , wherein a hot word of the one or more hot words is associated with a link action, and wherein modifying the document comprises including a link to another document, object, or network address within the document.
15. The computer-implemented method of claim 3 , wherein a hot word of the one or more hot words is associated with a sharing action, and wherein modifying the document comprises modifying access permissions of the document.
16. The computer-implemented method of claim 3 , wherein a hot word of the one or more hot words is associated with a content item action, and wherein modifying the document comprises modifying the document to include a content item.
17. The computer-implemented method of claim 3 , wherein a hot word of the one or more hot words is associated with an invite action, and wherein modifying the document comprises sending invites to access the document to one or more users.
18. A system comprising:
one or more processors; and
a non-transitory computer-readable storage medium storing executable instructions that, when executed by the one or more processors, cause the one or more processors to perform steps comprising:
accessing captured audio data including speech of one or more speakers, the captured audio data associated with a document;
transcribing the captured audio data into text representative of the speech;
identifying a first portion of the text associated with a candidate document modification; and
modifying the document based on the candidate document modification associated with the identified first portion of the text to include at least a second portion of the text.
19. A non-transitory computer-readable storage medium storing executable instructions that, when executed by one or more processors, cause the one or more processors to perform steps comprising:
accessing captured audio data including speech of one or more speakers, the captured audio data associated with a document;
transcribing the captured audio data into text representative of the speech;
identifying a first portion of the text that satisfies a modification rule, the modification rule specifying a modification to make to the document based on content of the text; and
in response to the modification rule being satisfied, modifying the document based on the specified modification to include at least a second portion of the text.