{"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/aves-animal-vocalization-encoder-based-on","title":"AVES: Animal Vocalization Encoder based on Self-Supervision","arxiv_id":"2210.14493","date":"2022-10-26","proceeding":null,"authors":["Masato Hagiwara"],"abstract":"The lack of annotated training data in bioacoustics hinders the use of large-scale neural network models trained in a supervised way. In order to leverage a large amount of unannotated audio data, we propose AVES (Animal Vocalization Encoder based on Self-Supervision), a self-supervised, transformer-based audio representation model for encoding animal vocalizations. We pretrain AVES on a diverse set of unannotated audio datasets and fine-tune them for downstream bioacoustics tasks. Comprehensive experiments with a suite of classification and detection tasks have shown that AVES outperforms all the strong baselines and even the supervised \"topline\" models trained on annotated audio classification datasets. The results also suggest that curating a small training subset related to downstream tasks is an efficient way to train high-quality audio representation models. We open-source our models at \\url{https://github.com/earthspecies/aves}.","url_abs":"https://arxiv.org/abs/2210.14493v1","url_pdf":"https://arxiv.org/pdf/2210.14493v1.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"aves-animal-vocalization-encoder-based-on","repo_url":"https://github.com/earthspecies/aves","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"aves-animal-vocalization-encoder-based-on","repo_url":"https://github.com/MindCode-4/code-11/tree/main/aves","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"aves-animal-vocalization-encoder-based-on","repo_url":"https://github.com/reeered/AVES-MindSpore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.14493","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.14493"}},"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/reeered/AVES-MindSpore","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindCode-4/code-11/tree/main/aves","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/earthspecies/aves","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"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":0,"samples":[{"code_sha256_prefix":"7903fb223185148c","entry":"load_config","repo":"earthspecies/aves","repo_kind":"official","path":"aves/aves.py","file_url":"https://github.com/earthspecies/aves/blob/HEAD/aves/aves.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7903fb223185148c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}