Capture every inspiring moment from a speech
User Testing: Siri
Prototyping: Sketch, Principle
the Key Scenario
Taking notes used to be like this…
There are two pain points:
1. how to capture every insightful moment from the speaker?
2. how to organize the notes and recall them easily?
What if leveraging the technology can accelerate the process?
Making note-taking effective and efficient
To solve the pain points mentioned above, I developed 3 key features – Timestamp, Keywords, and Mark, and explore different variations of how these feature are shown on the interface and how users will interact with them.
The key flow includes:
Realtime transcript -> Highlighting -> Auto-generate keywords -> Navigate through keywords
-> Insert highlights to the existing note
Since I am interested in emotion tracking, I will explore how the Emotion Recognition technology will get involved and enhance this experience. For example, via Tone Recognition technology, the system can detect the tone changes of the speaker and indicate where the audience needs to pay more attention. Maybe the system can connect the audience with wearables, the wearables will capture the audience’s biometrics, and knows which part causes resonance among these audience and the speaker can modify his/her speeches according to this data.