AIMAIM
Research

Fall 2023 – present

Evaluator Sound

A mobile and web app that helps musicians practice more effectively by reviewing music performance audio for extra, missed, or wrong notes, using the novel LadderSym (ICLR 2026) and Polytune (AAAI 2025) transformer models.

Evaluator project illustration
Drawing by Cecilia Ines Sanchez.

Evaluator Sound is a mobile and web app that helps musicians practice more effectively by listening to their playing. It uses spectrogram analysis and multi-modal transformers to tell correct from incorrect playing, detecting extra, missed, and wrong notes, and returns an annotated score so the player knows exactly what to correct.

The error-detection models, LadderSym (ICLR 2026) and Polytune (AAAI 2025), take performance audio as input and return an annotated music score.

Publications

Detecting Music Performance Errors with Transformers, AAAI 2025.

Team

  • Ropan Datta (Lead)
  • Benjamin "Ben" Shiue-Hal Chou (Graduate Mentor)