Advancing Multi-Instrument Music Transcription: Results from the 2025 AMT Challenge
Ojas Chaturvedi, Kayshav Bhardwaj, Tanay Gondil, Benjamin Shiue-Hal Chou, Kristen Yeon-Ji Yun, Yung-Hsiang Lu, Yujia Yan, Sungkyun Chang
TL;DR
This paper reports on the 2025 AMT Challenge, benchmarking multi-instrument music transcription progress, highlighting advances and ongoing challenges in polyphony and timbre variation.
Contribution
It introduces the 2025 AMT Challenge results, showcasing improvements and identifying future research directions in multi-instrument transcription.
Findings
Two teams outperformed the baseline MT3 model.
Significant progress in transcription accuracy was achieved.
Challenges remain in polyphony and timbre variation handling.
Abstract
This paper presents the results of the 2025 Automatic Music Transcription (AMT) Challenge, an online competition to benchmark progress in multi-instrument transcription. Eight teams submitted valid solutions; two outperformed the baseline MT3 model. The results highlight both advances in transcription accuracy and the remaining difficulties in handling polyphony and timbre variation. We conclude with directions for future challenges: broader genre coverage and stronger emphasis on instrument detection.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.