HookKern + MuQ
Model- Use HookKern to produce a Humdrum **kern lead sheet with melody and chords.
Converts popular-music audio into a sung-melody-and-chord lead sheet in Humdrum **kern. It does not reconstruct every instrument in a full arrangement.
Input
Supports inputs in formats such as mp3 / wav / flac / ogg / m4a / aac / aif / aiff / mp4 / mov / mkv
Supported formats
Output
Output: Humdrum **kern
Use case
Prepare and edit notation in score-writing software.
This tool is under maintenance. Please try again later.
Converts popular-music audio into a sung-melody-and-chord lead sheet in Humdrum **kern. It does not reconstruct every instrument in a full arrangement.
Scores apply only to the cited dataset, metric and model version. Leading this table does not mean a current world record or a result from this service. Capabilities and tests can justify prioritizing models without comparable scores.
Scores come from the cited public sources; blue rows are models available in this tool.
Values come from the linked public source. Row labels identify the test set or checkpoint; models without a matching result are omitted.
| Rank | Test setting | Model | Symbol error rate (%) ↓ |
|---|---|---|---|
| #1 | Quartets · classical string quartets · augmentation | HookKern + MuQTelkNetPaper Table 2 | 4.98Best |
| #2 | Quartets · classical string quartets | Alfaro-Contreras et al.Prior SOTA cited by paper | 15.30 |
Scores come from the linked base checkpoint, not a new measurement of the model running here.
| Test setting | Model | Symbol error rate (%) ↓ |
|---|---|---|
| SheetSage-A2S · popular lead sheets · augmentation | HookKern + MuQTelkNetPaper Table 2 | 20.92 |
ACM Multimedia - 2026
Include the tool name, steps and the problem in your feedback. Screenshots can help us locate it.
Demo
Converts popular-music audio into a sung-melody-and-chord lead sheet in Humdrum **kern. It does not reconstruct every instrument in a full arrangement.
1 audio tracks
TelkNet · HookKern · E3 · 30 sec
Engraving the score…
ChordMini BTC
Import SF2/SF3, up to 512 MB per file. Files stay on this page locally and are not uploaded; transcription notes stay unchanged.
For audio or video projects at 48 kHz. Files are slightly larger.
WAV is synthesized directly at the chosen format using the current sounds, speed and volume. Sound quality also depends on the sound library; more bits cannot improve its source samples.