Participants in a voice call often exchange small yet important pieces of information, e.g., phone numbers, meeting locations, action items, etc. To capture such information, users often interrupt call flow to take down notes, which is an inconvenience. This disclosure describes machine-learning techniques that automatically detect and capture (with permission from the participants to the call) noteworthy pieces of information that are detected in the audio flow between the participants.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.