{"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/cocola-coherence-oriented-contrastive","title":"COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations","arxiv_id":"2404.16969","date":"2024-04-25","proceeding":null,"authors":["Ruben Ciranni","Giorgio Mariani","Michele Mancusi","Emilian Postolache","Giorgio Fabbro","Emanuele Rodolà","Luca Cosmo"],"abstract":"We present COCOLA (Coherence-Oriented Contrastive Learning for Audio), a contrastive learning method for musical audio representations that captures the harmonic and rhythmic coherence between samples. Our method operates at the level of the stems composing music tracks and can input features obtained via Harmonic-Percussive Separation (HPS). COCOLA allows the objective evaluation of generative models for music accompaniment generation, which are difficult to benchmark with established metrics. In this regard, we evaluate recent music accompaniment generation models, demonstrating the effectiveness of the proposed method. We release the model checkpoints trained on public datasets containing separate stems (MUSDB18-HQ, MoisesDB, Slakh2100, and CocoChorales).","url_abs":"https://arxiv.org/abs/2404.16969v4","url_pdf":"https://arxiv.org/pdf/2404.16969v4.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":"cocola-coherence-oriented-contrastive","repo_url":"https://github.com/emilianpostolache/stable-audio-controlnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"cocola-coherence-oriented-contrastive","repo_url":"https://github.com/gladia-research-group/cocola","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"music-generation","task_name":"Music Generation"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.16969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.16969"}},"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/gladia-research-group/cocola","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/emilianpostolache/stable-audio-controlnet","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":2,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":2,"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":"ab52a777f7ea129a","entry":"get_logger","repo":"emilianpostolache/stable-audio-controlnet","repo_kind":"official","path":"main/utils.py","file_url":"https://github.com/emilianpostolache/stable-audio-controlnet/blob/HEAD/main/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ab52a777f7ea129a"}},{"code_sha256_prefix":"4650aeb06e5b390d","entry":"low_pass_filter","repo":"emilianpostolache/stable-audio-controlnet","repo_kind":"official","path":"main/module_controlnet_envelope.py","file_url":"https://github.com/emilianpostolache/stable-audio-controlnet/blob/HEAD/main/module_controlnet_envelope.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"4650aeb06e5b390d"}},{"code_sha256_prefix":"8d8797c7e11715cf","entry":"create_model_from_config","repo":"emilianpostolache/stable-audio-controlnet","repo_kind":"official","path":"main/controlnet/factory.py","file_url":"https://github.com/emilianpostolache/stable-audio-controlnet/blob/HEAD/main/controlnet/factory.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"8d8797c7e11715cf"}},{"code_sha256_prefix":"a47d8ad429baceb6","entry":"get_wandb_logger","repo":"emilianpostolache/stable-audio-controlnet","repo_kind":"official","path":"main/module_controlnet_audio.py","file_url":"https://github.com/emilianpostolache/stable-audio-controlnet/blob/HEAD/main/module_controlnet_audio.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a47d8ad429baceb6"}},{"code_sha256_prefix":"2e52d323f6477f9a","entry":"window_rms","repo":"emilianpostolache/stable-audio-controlnet","repo_kind":"official","path":"main/module_controlnet_envelope.py","file_url":"https://github.com/emilianpostolache/stable-audio-controlnet/blob/HEAD/main/module_controlnet_envelope.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"2e52d323f6477f9a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}