Experience lab
Score Lens
See the structure inside the score.
The Music Analyzer tests whether interpretable measurements from orchestral scores can surface musically meaningful passages. Score Lens is one public UX slice: controlled natural-language retrieval over analysed score segments, aligned to real recordings for immediate listening.
Conceived as part of the next markslater composer website experience; showcased here as work in progress.
Try the demo ↗Live natural-language music discovery demo
Personal introduction + guided walkthroughMARK SLATER
01
The opportunity
Designed for Composers, orchestrators, music technologists and curious listeners
Music analysis often produces either specialist notation or broad descriptive language. Score Lens explores a third possibility: an evidence-led visual experience that lets people move between the score, sound and musical interpretation.
Working now
- ✓Controlled natural-language search across 28 analysed passages from three selected tracks
- ✓Cue-accurate Tone.js audio playback with a persistent waveform player
- ✓Deterministic matching over prepared analysis and reviewed descriptive tags
- ✓MIDI-derived segmentation and musical measurements with MusicXML score context where available
Next on the roadmap
- 01Expand discovery across more cues and analysis layers
- 02Connect the public interaction to the full catalogue and conversational service
- 03Bring the strongest interactions into the future composer website
02
Project in brief
“What makes an orchestral passage feel tense, suspended, inevitable or finally resolved? The Music Analyzer tests whether some of the trained understanding used by composers and orchestrators can be surfaced from computer-readable scores. Working with real orchestral recordings aligned to MIDI and MusicXML, it examines instrumentation, tempo, density, dynamics, texture, dissonance, energy, tension and change over time. Score Lens is one public window into the research: describe a musical moment, inspect the match and hear the passage from its exact point in the recording.”
PythonMIDIMusicXMLReact / TypeScriptTime-aligned audio