{"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/can-self-supervised-neural-networks-pre","title":"Can Self-Supervised Neural Representations Pre-Trained on Human Speech distinguish Animal Callers?","arxiv_id":"2305.14035","date":"2023-05-23","proceeding":null,"authors":["Eklavya Sarkar","Mathew Magimai. -Doss"],"abstract":"Self-supervised learning (SSL) models use only the intrinsic structure of a given signal, independent of its acoustic domain, to extract essential information from the input to an embedding space. This implies that the utility of such representations is not limited to modeling human speech alone. Building on this understanding, this paper explores the cross-transferability of SSL neural representations learned from human speech to analyze bio-acoustic signals. We conduct a caller discrimination analysis and a caller detection study on Marmoset vocalizations using eleven SSL models pre-trained with various pretext tasks. The results show that the embedding spaces carry meaningful caller information and can successfully distinguish the individual identities of Marmoset callers without fine-tuning. This demonstrates that representations pre-trained on human speech can be effectively applied to the bio-acoustics domain, providing valuable insights for future investigations in this field.","url_abs":"https://arxiv.org/abs/2305.14035v3","url_pdf":"https://arxiv.org/pdf/2305.14035v3.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":"can-self-supervised-neural-networks-pre","repo_url":"https://github.com/idiap/ssl-caller-detection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"caller-detection","task_name":"Caller Detection"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"speaker-recognition","task_name":"Speaker Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2305.14035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14035"}},"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/idiap/ssl-caller-detection","reach":null}],"summary":{"ran_honours":2,"ran_draft_wrong":4,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"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":7,"samples":[{"code_sha256_prefix":"f88dfdeca68a625f","entry":"compute_eer","repo":"idiap/ssl-caller-detection","repo_kind":"official","path":"src/classifier_caller_groups.py","file_url":"https://github.com/idiap/ssl-caller-detection/blob/HEAD/src/classifier_caller_groups.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"f88dfdeca68a625f"}},{"code_sha256_prefix":"0e4afdfcb4078382","entry":"create_grid","repo":"idiap/ssl-caller-detection","repo_kind":"official","path":"src/classifier_caller_groups.py","file_url":"https://github.com/idiap/ssl-caller-detection/blob/HEAD/src/classifier_caller_groups.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":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"0e4afdfcb4078382"}},{"code_sha256_prefix":"9be3680cccfbba85","entry":"get_features","repo":"idiap/ssl-caller-detection","repo_kind":"official","path":"src/extract_features.py","file_url":"https://github.com/idiap/ssl-caller-detection/blob/HEAD/src/extract_features.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"9be3680cccfbba85"}},{"code_sha256_prefix":"d5d479ec07a80968","entry":"make_dict_json_serializable","repo":"idiap/ssl-caller-detection","repo_kind":"official","path":"src/classifier_caller_groups.py","file_url":"https://github.com/idiap/ssl-caller-detection/blob/HEAD/src/classifier_caller_groups.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":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"d5d479ec07a80968"}},{"code_sha256_prefix":"f0248e041469de8c","entry":"randomColorGenerator","repo":"idiap/ssl-caller-detection","repo_kind":"official","path":"src/compile_results.py","file_url":"https://github.com/idiap/ssl-caller-detection/blob/HEAD/src/compile_results.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"f0248e041469de8c"}},{"code_sha256_prefix":"9926abee811d65a9","entry":"verify_layer_id","repo":"idiap/ssl-caller-detection","repo_kind":"official","path":"src/extract_features.py","file_url":"https://github.com/idiap/ssl-caller-detection/blob/HEAD/src/extract_features.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":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"9926abee811d65a9"}},{"code_sha256_prefix":"6fb96fdea5fcc9b3","entry":"make_fpr_tpr_auc_dicts","repo":"idiap/ssl-caller-detection","repo_kind":"official","path":"src/compile_results.py","file_url":"https://github.com/idiap/ssl-caller-detection/blob/HEAD/src/compile_results.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"6fb96fdea5fcc9b3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}