Tao Qin, Tie-Yan Liu, Rui Wang, Xu Tan, Mingliang Zeng, Zeqian Ju
We lifted 7 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| microsoft/muzic | — | 3 of 7 |
| Function | Status | Where it lives |
|---|---|---|
| b2e | Ran | microsoft/muzic/musicbert/preprocess.py code served (permissive licence) · get_code("080d0c696a0a9941") |
| time_signature_reduce | Ran | microsoft/muzic/musicbert/preprocess.py code served (permissive licence) · get_code("21c2e5101ac354b8") |
| v2e | Ran | microsoft/muzic/musicbert/preprocess.py code served (permissive licence) · get_code("1aa2ba272297146c") |
| MIDI_to_encoding | Not yet run | microsoft/muzic/musicbert/preprocess.py code served (permissive licence) · get_code("eff932c4fe4749ec") |
| d2e | Not yet run | microsoft/muzic/musicbert/preprocess.py code served (permissive licence) · get_code("7b272edf71fd390f") |
| e2t | Not yet run | microsoft/muzic/musicbert/preprocess.py code served (permissive licence) · get_code("f3d2948c891c6d3b") |
| t2e | Not yet run | microsoft/muzic/musicbert/preprocess.py code served (permissive licence) · get_code("4b737a6cdd8ef10d") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Symbolic music understanding, which refers to the understanding of music from the symbolic data (e.g., MIDI format, but not audio), covers many music applications such as genre classification, emotion classification, and music pieces matching. While good music representations are beneficial for these applications, the lack of training data hinders representation learning. Inspired by the success of pre-training models in natural language processing, in this paper, we develop MusicBERT, a large-scale pre-trained model for music understanding. To this end, we construct a large-scale symbolic music corpus that contains more than 1 million music songs. Since symbolic music contains more structural (e.g., bar, position) and diverse information (e.g., tempo, instrument, and pitch), simply adopting the pre-training techniques from NLP to symbolic music only brings marginal gains. Therefore, we design several mechanisms, including OctupleMIDI encoding and bar-level masking strategy, to enhance pre-training with symbolic music data. Experiments demonstrate the advantages of MusicBERT on four music understanding tasks, including melody completion, accompaniment suggestion, genre classification, and style classification. Ablation studies also verify the effectiveness of our designs of OctupleMIDI encoding and barlevel masking strategy in MusicBERT.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2106.05630")
get_code_for_paper("2106.05630")
have("2106.05630")
Connect an agent — have() is free.