{"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-unified-model-for-zero-shot-music-source","title":"A Unified Model for Zero-shot Music Source Separation, Transcription and Synthesis","arxiv_id":"2108.03456","date":"2021-08-07","proceeding":null,"authors":["Liwei Lin","Qiuqiang Kong","Junyan Jiang","Gus Xia"],"abstract":"We propose a unified model for three inter-related tasks: 1) to \\textit{separate} individual sound sources from a mixed music audio, 2) to \\textit{transcribe} each sound source to MIDI notes, and 3) to\\textit{ synthesize} new pieces based on the timbre of separated sources. The model is inspired by the fact that when humans listen to music, our minds can not only separate the sounds of different instruments, but also at the same time perceive high-level representations such as score and timbre. To mirror such capability computationally, we designed a pitch-timbre disentanglement module based on a popular encoder-decoder neural architecture for source separation. The key inductive biases are vector-quantization for pitch representation and pitch-transformation invariant for timbre representation. In addition, we adopted a query-by-example method to achieve \\textit{zero-shot} learning, i.e., the model is capable of doing source separation, transcription, and synthesis for \\textit{unseen} instruments. The current design focuses on audio mixtures of two monophonic instruments. Experimental results show that our model outperforms existing multi-task baselines, and the transcribed score serves as a powerful auxiliary for separation tasks.","url_abs":"https://arxiv.org/abs/2108.03456v1","url_pdf":"https://arxiv.org/pdf/2108.03456v1.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":"abstracts"},"code_links":[{"paper_slug":"a-unified-model-for-zero-shot-music-source","repo_url":"https://github.com/kikyo-16/a-unified-model-for-zero-shot-musical-source-separation-transcription-and-synthesis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"music-source-separation","task_name":"Music Source Separation"},{"task_slug":"music-transcription","task_name":"Music Transcription"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.03456","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.03456"}},"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/kikyo-16/a-unified-model-for-zero-shot-musical-source-separation-transcription-and-synthesis","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"3d7b9c32fb8fdef4","entry":"ave_val","repo":"kikyo-16/a-unified-model-for-zero-shot-musical-source-separation-transcription-and-synthesis","repo_kind":"official","path":"src/analyze/utilities.py","file_url":"https://github.com/kikyo-16/a-unified-model-for-zero-shot-musical-source-separation-transcription-and-synthesis/blob/HEAD/src/analyze/utilities.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3d7b9c32fb8fdef4"}},{"code_sha256_prefix":"645dc370e91c4d38","entry":"compute_results","repo":"kikyo-16/a-unified-model-for-zero-shot-musical-source-separation-transcription-and-synthesis","repo_kind":"official","path":"src/analyze/utilities.py","file_url":"https://github.com/kikyo-16/a-unified-model-for-zero-shot-musical-source-separation-transcription-and-synthesis/blob/HEAD/src/analyze/utilities.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"645dc370e91c4d38"}},{"code_sha256_prefix":"c7118f4e5f88879b","entry":"device","repo":"kikyo-16/a-unified-model-for-zero-shot-musical-source-separation-transcription-and-synthesis","repo_kind":"official","path":"src/inference/inference.py","file_url":"https://github.com/kikyo-16/a-unified-model-for-zero-shot-musical-source-separation-transcription-and-synthesis/blob/HEAD/src/inference/inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c7118f4e5f88879b"}},{"code_sha256_prefix":"02716b8d9b772857","entry":"get_register","repo":"kikyo-16/a-unified-model-for-zero-shot-musical-source-separation-transcription-and-synthesis","repo_kind":"official","path":"src/inference/inference.py","file_url":"https://github.com/kikyo-16/a-unified-model-for-zero-shot-musical-source-separation-transcription-and-synthesis/blob/HEAD/src/inference/inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"02716b8d9b772857"}},{"code_sha256_prefix":"0dd3dd04e178bae9","entry":"seen","repo":"kikyo-16/a-unified-model-for-zero-shot-musical-source-separation-transcription-and-synthesis","repo_kind":"official","path":"src/analyze/utilities.py","file_url":"https://github.com/kikyo-16/a-unified-model-for-zero-shot-musical-source-separation-transcription-and-synthesis/blob/HEAD/src/analyze/utilities.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0dd3dd04e178bae9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}