{"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/clapsep-leveraging-contrastive-pre-trained","title":"CLAPSep: Leveraging Contrastive Pre-trained Model for Multi-Modal Query-Conditioned Target Sound Extraction","arxiv_id":"2402.17455","date":"2024-02-27","proceeding":null,"authors":["Hao Ma","Zhiyuan Peng","Xu Li","Mingjie Shao","Xixin Wu","Ju Liu"],"abstract":"Universal sound separation (USS) aims to extract arbitrary types of sounds from real-world recordings. This can be achieved by language-queried target sound extraction (TSE), which typically consists of two components: a query network that converts user queries into conditional embeddings, and a separation network that extracts the target sound accordingly. Existing methods commonly train models from scratch. As a consequence, substantial data and computational resources are required to make the randomly initialized model comprehend sound events and perform separation accordingly. In this paper, we propose to integrate pre-trained models into TSE models to address the above issue. To be specific, we tailor and adapt the powerful contrastive language-audio pre-trained model (CLAP) for USS, denoted as CLAPSep. CLAPSep also accepts flexible user inputs, taking both positive and negative user prompts of uni- and/or multi-modalities for target sound extraction. These key features of CLAPSep can not only enhance the extraction performance but also improve the versatility of its application. We provide extensive experiments on 5 diverse datasets to demonstrate the superior performance and zero- and few-shot generalizability of our proposed CLAPSep with fast training convergence, surpassing previous methods by a significant margin. Full codes and some audio examples are released for reproduction and evaluation.","url_abs":"https://arxiv.org/abs/2402.17455v5","url_pdf":"https://arxiv.org/pdf/2402.17455v5.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":"clapsep-leveraging-contrastive-pre-trained","repo_url":"https://github.com/aisaka0v0/clapsep","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"target-sound-extraction","task_name":"Target Sound Extraction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/target-sound-extraction-on-audiocaps","task":"Target Sound Extraction","dataset":"AudioCaps","model":"CLAPSep","rank_in_archive_order":1,"of":1,"metrics":{"SDRi":"10.08","SI-SDRi":"9.40"},"uses_additional_data":false},{"leaderboard":"/sota/target-sound-extraction-on-audioset","task":"Target Sound Extraction","dataset":"AudioSet","model":"CLAPSep","rank_in_archive_order":1,"of":1,"metrics":{"SDRi":"9.29","SI-SDRi":"8.44"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.17455","atlas_url":"https://app.syntology.ai/?focus=2402.17455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17455"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/aisaka0v0/clapsep","reach":{"status":"ok"}}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":"8e7fce2bb7365742","entry":"load_checkpoint","repo":"aisaka0v0/clapsep","repo_kind":"official","path":"helpers/utils.py","file_url":"https://github.com/aisaka0v0/clapsep/blob/HEAD/helpers/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8e7fce2bb7365742"}},{"code_sha256_prefix":"9a053c56d1d332e3","entry":"loss_fn","repo":"aisaka0v0/clapsep","repo_kind":"official","path":"model/CLAPSep.py","file_url":"https://github.com/aisaka0v0/clapsep/blob/HEAD/model/CLAPSep.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9a053c56d1d332e3"}},{"code_sha256_prefix":"c481103177a670c9","entry":"model_size","repo":"aisaka0v0/clapsep","repo_kind":"official","path":"helpers/utils.py","file_url":"https://github.com/aisaka0v0/clapsep/blob/HEAD/helpers/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c481103177a670c9"}},{"code_sha256_prefix":"596dd36d02e6ffdb","entry":"run_time","repo":"aisaka0v0/clapsep","repo_kind":"official","path":"helpers/utils.py","file_url":"https://github.com/aisaka0v0/clapsep/blob/HEAD/helpers/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"596dd36d02e6ffdb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}