About ChordMini

Enhancing Automatic Chord Recognition via Pseudo-Labeling and Knowledge Distillation

Automatic Chord Recognition (ACR) is constrained by the scarcity of aligned chord labels, as well-aligned annotations are costly to acquire. At the same time, open-weight pre-trained models are currently more accessible than their proprietary training data. In this work, we present a two-stage training pipeline that leverages pre-trained models together with unlabeled audio. The proposed method decouples training into two stages. In the first stage, we use a pre-trained BTC model as a teacher to generate pseudo-labels for over 1,000 hours of diverse unlabeled audio and train a student model solely on these pseudo-labels. In the second stage, the student is continually trained on ground-truth labels as they become available, with selective knowledge distillation (KD) from the teacher applied as a regularizer to prevent catastrophic forgetting of the representations learned in the first stage. In our experiments, two models (BTC, 2E1D) were used as students. In stage 1, using only pseudo-labels, the BTC student achieves over 98% of the teacher's performance, while the 2E1D model achieves about 96% across seven standard mir_eval metrics. After a single training run for both students in stage 2, the resulting BTC student model surpasses the traditional supervised learning baseline by 2.5% and the original pre-trained teacher model by 1.55% on average across all metrics. The resulting 2E1D student model improves from the traditional supervised learning baseline by 3.79% on average and achieves almost the same performance as the teacher. Both cases show large gains on rare chord qualities.

arXiv:2602.19778 [cs.SD]

Nghia Phan, Rong Jin, Gang Liu, Xiao Dong

@misc{phan2026enhancingautomaticchordrecognition,
      title={Enhancing Automatic Chord Recognition via Pseudo-Labeling and Knowledge Distillation}, 
      author={Nghia Phan and Rong Jin and Gang Liu and Xiao Dong},
      year={2026},
      eprint={2602.19778},
      archivePrefix={arXiv},
      primaryClass={cs.SD},
      url={https://arxiv.org/abs/2602.19778}, 
}

ChordMini is built upon the excellent work of many open-source projects and services. We gratefully acknowledge the following third-party libraries and services:

We extend our sincere gratitude to all the developers and maintainers of these projects for making their work available to the open-source community.

For research inquiries, collaboration opportunities, or technical questions, please contact: