Fall 2024 – present
Automatic Music Transcription
Streamlining audio-to-MIDI transcription for musicians and educators, with applications in isolating sounds in noisy environments.
Automatic Music Transcription is a project focused on streamlining audio-to-MIDI transcription for musicians and educators, with applications in isolating sounds in noisy environments. We are conducting a systematic review of AMT models, examining their strengths and limitations with complex, multi-instrument music.
In April 2025 we hosted a competition challenging participants to create accurate transcription models for classical music. Currently, we are building our own interpretable AMT model, as well as focusing on other niches such as using computer vision to generate guitar tablature and quantifying a music piece's “complexity” as inputs for future AMT models.
Competition
The 2025 Music Transcription Competition is documented in full, including the live leaderboard.
Team
- Ojas Chaturvedi (Lead)
- Kayshav Bhardwaj (Co-lead)