{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-multi-scale-attentive-transformer-for-multi","title":"A Multi-Scale Attentive Transformer for Multi-Instrument Symbolic Music Generation","arxiv_id":"2305.16592","date":"2023-05-26","proceeding":null,"authors":["Xipin Wei","Junhui Chen","Zirui Zheng","Li Guo","Lantian Li","Dong Wang"],"abstract":"Recently, multi-instrument music generation has become a hot topic. Different from single-instrument generation, multi-instrument generation needs to consider inter-track harmony besides intra-track coherence. This is usually achieved by composing note segments from different instruments into a signal sequence. This composition could be on different scales, such as note, bar, or track. Most existing work focuses on a particular scale, leading to a shortage in modeling music with diverse temporal and track dependencies. This paper proposes a multi-scale attentive Transformer model to improve the quality of multi-instrument generation. We first employ multiple Transformer decoders to learn multi-instrument representations of different scales and then design an attentive mechanism to fuse the multi-scale information. Experiments conducted on SOD and LMD datasets show that our model improves both quantitative and qualitative performance compared to models based on single-scale information. The source code and some generated samples can be found at https://github.com/HaRry-qaq/MSAT.","url_abs":"https://arxiv.org/abs/2305.16592v1","url_pdf":"https://arxiv.org/pdf/2305.16592v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"a-multi-scale-attentive-transformer-for-multi","repo_url":"https://github.com/harry-qaq/msat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.16592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16592"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/harry-qaq/msat","reach":null}],"summary":{"ran_honours":3,"ran_draft_wrong":1,"ran_fixture":1},"by_repo_kind":{"official":{"samples":5,"ran":5,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":5,"samples":[{"code_sha256_prefix":"c62692790c5f491e","entry":"get_cut_beat","repo":"harry-qaq/msat","repo_kind":"official","path":"MSAT/msat/generate.py","file_url":"https://github.com/harry-qaq/msat/blob/HEAD/MSAT/msat/generate.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c62692790c5f491e"}},{"code_sha256_prefix":"ff2c02d0db501ea9","entry":"get_instrument_beat","repo":"harry-qaq/msat","repo_kind":"official","path":"MSAT/msat/generate.py","file_url":"https://github.com/harry-qaq/msat/blob/HEAD/MSAT/msat/generate.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ff2c02d0db501ea9"}},{"code_sha256_prefix":"0a445b874ed99626","entry":"get_lr_multiplier","repo":"harry-qaq/msat","repo_kind":"official","path":"MSAT/msat/train_multi_scale.py","file_url":"https://github.com/harry-qaq/msat/blob/HEAD/MSAT/msat/train_multi_scale.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0a445b874ed99626"}},{"code_sha256_prefix":"ccca785143f55523","entry":"parse_args","repo":"harry-qaq/msat","repo_kind":"official","path":"MSAT/evaluate/evaluate-local.py","file_url":"https://github.com/harry-qaq/msat/blob/HEAD/MSAT/evaluate/evaluate-local.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ccca785143f55523"}},{"code_sha256_prefix":"f42973d54d5029d9","entry":"train_one_epoch_for_enc1","repo":"harry-qaq/msat","repo_kind":"official","path":"MSAT/msat/train_multi_scale.py","file_url":"https://github.com/harry-qaq/msat/blob/HEAD/MSAT/msat/train_multi_scale.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f42973d54d5029d9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}