BACHI: Boundary-Aware Symbolic Chord Recognition Data for Pop and Classical Music

Trained model weights and datasets for the BACHI chord recognition system. The data supports the paper 'BACHI: Boundary-Aware Symbolic Chord Recognition Through Masked Iterative Decoding on Pop and Classical Music' by Mingyang Yao and Ke Chen, accepted for ICASSP 2026. The dataset page was last updated on 2026-01 17.

Use Cases

• Training boundary-aware chord recognition models based on the described masked iterative decoding method.
• Benchmarking chord recognition algorithms on pop and classical music genres mentioned in the description.
• Developing music information retrieval tools for symbolic music analysis.
• Studying chord progression patterns in pop and classical compositions.

Strengths

• Dataset is associated with a peer-reviewed paper accepted for a major conference (ICASSP 2026).
• Includes trained model weights, providing a starting point for researchers.
• Focuses on two distinct music genres (pop and classical) as stated in the title.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

Itsuki-music on Hugging Face, associated with academic research by Mingyang Yao and Ke Chen.

Collection Method

Likely contains symbolic music data and model outputs from the BACHI research project.

Time Range

null

Freshness

Last updated 2026-01-17 20:17:41; freshness should be verified.

Geography

null