Exploring Real-time Visualisations to Support Chord Learning...
summary
A prototype web app called Jam with Jamendo queries Jamendo’s ~200,000-track API and serves songs whose automatic chord transcription (confidence score included) exactly matches a user’s selected chords; about 100,000 tracks are preprocessed into a MongoDB and served by a Flask backend with JavaScript/jQuery frontend. The app limits outputs to five chord qualities, returns an average of seven chords per query, and a 7‑participant (21 trials) pilot shows a clear preference for the linear vs circular visualisations over the chromatic circle mapping for clarity.
AI-written summary · about
chapters (13)
- 0:00Introduction to project
- 1:26Web app workflow explained
- 3:42Chord transcription automation
- 5:48Jamendo dataset overview
- 7:13Backend architecture details
- 8:40Visualization types demo
- 9:22User study methodology
- 10:40User experience video
- 12:48User study results
- 13:54Chord query preferences
- 15:00Design feedback and lessons
- 15:43Future work plans
- 17:14Q&A session
related talks
21mMusical Charts: Using OSS to Make Data Visualizations Accessible to Visually Impaired Users
10mInteractive Music Genre Exploration with Visualization and Mood Control
28mBuilding apps with D3.js
27mUsing Dash to Create Interactive Web Apps for Non-Technical Audiences
47mData, Design, Code
41mData, Design, Code
40mBuilding A Folk Music Recommendation System with LLMs
50mBetter Spotify Playlists through Music Theory & Discrete Optimization