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 a text transcript representative of the speech;
identifying, by the content creation system, a portion of the text transcript associated with an action to generate a text outline;
generating the text outline, the text outline including one or more main points or topics of the text transcript; and
modifying, by the content creation system, the document to incorporate the generated text outline.
2. The computer-implemented method of claim 1 , wherein the portion of the text transcript includes a hot word, and wherein the generating of the text outline occurs responsive to detecting the hot word.
3. The computer-implemented method of claim 1 , wherein generating the text outline further comprises identifying one or more user identities associated with the one or more main points or topics of the text transcript.
4. The computer-implemented method of claim 1 , wherein the one or more main points or topics of the text transcript are identified based on predefined keywords.
5. The computer-implemented method of claim 4 , wherein a keyword of the predefined keywords identifies a due date associated with an action item.
6. The computer-implemented method of claim 4 , wherein a keyword of the predefined keywords identifies a decision action, and wherein generating the text outline comprises including text within the text outline identifying the decision action.
7. The computer-implemented method of claim 4 , wherein a keyword of the predefined keywords identifies an assignment action, and wherein generating the text outline comprises including text within the text outline identifying the assignment action.
8. The computer-implemented method of claim 7 , wherein the assignment made during the speech is associated with a task, and wherein generating the text outline comprises including text within the text outline identifying the task.
9. The computer-implemented method of claim 8 , wherein modifying the document further comprises including a status indicator representative of a status of the task.
10. The computer-implemented method of claim 8 , wherein modifying the document further comprises tagging one or more users to whom the task is assigned within the document.
11. The computer-implemented method of claim 1 , wherein modifying the document to incorporate the generated text outline comprises embedding the generated text outline at a top of the document.
12. The computer-implemented method of claim 1 , wherein modifying the document to incorporate the generated text outline comprises associating portions of the generated text outline with audio playback elements displayed in conjunction with or next to the portions.
13. 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, 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 a text transcript representative of the speech;
identifying, by the content creation system, a portion of the text transcript associated with an action to generate a text outline;
generating the text outline, the text outline including one or more main points or topics of the text transcript; and
modifying, by the content creation system, the document to incorporate the generated text outline.
14. The system of claim 13 , wherein the portion of the text transcript includes a hot word, and wherein the generating of the text outline occurs responsive to detecting the hot word.
15. The system of claim 13 , wherein generating the text outline further comprises identifying one or more user identities associated with the one or more main points or topics of the text transcript.
16. The system of claim 13 , wherein the one or more main points or topics of the text transcript are identified based on predefined keywords.
17. The system of claim 16 , wherein a keyword of the predefined keywords identifies a due date associated with an action item.
18. The system of claim 16 , wherein a keyword of the predefined keywords identifies a decision action, and wherein generating the text outline comprises including text within the text outline identifying the decision action.
19. The system of claim 16 , wherein a keyword of the predefined keywords identifies an assignment action, and wherein generating the text outline comprises including text within the text outline identifying the assignment action.
20. 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, 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 a text transcript representative of the speech;
identifying, by the content creation system, a portion of the text transcript associated with an action to generate a text outline;
generating the text outline, the text outline including one or more main points or topics of the text transcript; and
modifying, by the content creation system, the document to incorporate the generated text outline.