{"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/byol-s-learning-self-supervised-speech","title":"BYOL-S: Learning Self-supervised Speech Representations by Bootstrapping","arxiv_id":"2206.12038","date":"2022-06-24","proceeding":null,"authors":["Gasser Elbanna","Neil Scheidwasser-Clow","Mikolaj Kegler","Pierre Beckmann","Karl El Hajal","Milos Cernak"],"abstract":"Methods for extracting audio and speech features have been studied since pioneering work on spectrum analysis decades ago. Recent efforts are guided by the ambition to develop general-purpose audio representations. For example, deep neural networks can extract optimal embeddings if they are trained on large audio datasets. This work extends existing methods based on self-supervised learning by bootstrapping, proposes various encoder architectures, and explores the effects of using different pre-training datasets. Lastly, we present a novel training framework to come up with a hybrid audio representation, which combines handcrafted and data-driven learned audio features. All the proposed representations were evaluated within the HEAR NeurIPS 2021 challenge for auditory scene classification and timestamp detection tasks. Our results indicate that the hybrid model with a convolutional transformer as the encoder yields superior performance in most HEAR challenge tasks.","url_abs":"https://arxiv.org/abs/2206.12038v4","url_pdf":"https://arxiv.org/pdf/2206.12038v4.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":"byol-s-learning-self-supervised-speech","repo_url":"https://github.com/gasserelbanna/serab-byols","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"scene-classification","task_name":"Scene Classification"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/self-supervised-learning-on-crema-d","task":"Self-Supervised Learning","dataset":"CREMA-D","model":"Hybrid BYOL-S/CvT","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"67.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.12038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.12038"}},"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/gasserelbanna/serab-byols","reach":null}],"summary":{"ran_honours":1,"ran":3,"unverified":3},"by_repo_kind":{"official":{"samples":6,"ran":3,"repositories":1},"community":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"7c4c739eb8bf27eb","entry":"get_model_feature_d","repo":"nttcslab/byol-a","repo_kind":"community","path":"evaluate.py","file_url":"https://github.com/nttcslab/byol-a/blob/HEAD/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7c4c739eb8bf27eb"}},{"code_sha256_prefix":"f347d69f03a546ff","entry":"BYOL","repo":"gasserelbanna/serab-byols","repo_kind":"official","path":"byol_a/byol_pytorch.py","file_url":"https://github.com/gasserelbanna/serab-byols/blob/HEAD/byol_a/byol_pytorch.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":"f347d69f03a546ff"}},{"code_sha256_prefix":"f80bb0684b28c2b5","entry":"MLP","repo":"gasserelbanna/serab-byols","repo_kind":"official","path":"byol_a/byol_pytorch.py","file_url":"https://github.com/gasserelbanna/serab-byols/blob/HEAD/byol_a/byol_pytorch.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":"f80bb0684b28c2b5"}},{"code_sha256_prefix":"9067d258b8cacd0a","entry":"NetWrapper","repo":"gasserelbanna/serab-byols","repo_kind":"official","path":"byol_a/byol_pytorch.py","file_url":"https://github.com/gasserelbanna/serab-byols/blob/HEAD/byol_a/byol_pytorch.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":"9067d258b8cacd0a"}},{"code_sha256_prefix":"eb00fc7fcbc4b8ff","entry":"default","repo":"GasserElbanna/serab-byols","repo_kind":"official","path":"byol_a/byol_pytorch.py","file_url":"https://github.com/GasserElbanna/serab-byols/blob/HEAD/byol_a/byol_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eb00fc7fcbc4b8ff"}},{"code_sha256_prefix":"b1e8cbc9095c2699","entry":"flatten","repo":"GasserElbanna/serab-byols","repo_kind":"official","path":"byol_a/byol_pytorch.py","file_url":"https://github.com/GasserElbanna/serab-byols/blob/HEAD/byol_a/byol_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b1e8cbc9095c2699"}},{"code_sha256_prefix":"d667df1dc044d767","entry":"singleton","repo":"GasserElbanna/serab-byols","repo_kind":"official","path":"byol_a/byol_pytorch.py","file_url":"https://github.com/GasserElbanna/serab-byols/blob/HEAD/byol_a/byol_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d667df1dc044d767"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}