{"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/wavefake-a-data-set-to-facilitate-audio","title":"WaveFake: A Data Set to Facilitate Audio Deepfake Detection","arxiv_id":"2111.02813","date":"2021-11-04","proceeding":null,"authors":["Joel Frank","Lea Schönherr"],"abstract":"Deep generative modeling has the potential to cause significant harm to society. Recognizing this threat, a magnitude of research into detecting so-called \"Deepfakes\" has emerged. This research most often focuses on the image domain, while studies exploring generated audio signals have, so-far, been neglected. In this paper we make three key contributions to narrow this gap. First, we provide researchers with an introduction to common signal processing techniques used for analyzing audio signals. Second, we present a novel data set, for which we collected nine sample sets from five different network architectures, spanning two languages. Finally, we supply practitioners with two baseline models, adopted from the signal processing community, to facilitate further research in this area.","url_abs":"https://arxiv.org/abs/2111.02813v1","url_pdf":"https://arxiv.org/pdf/2111.02813v1.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":"wavefake-a-data-set-to-facilitate-audio","repo_url":"https://github.com/rub-syssec/wavefake","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"wavefake-a-data-set-to-facilitate-audio","repo_url":"https://github.com/audio-df-ucb/clonedvoicedetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"audio-deepfake-detection","task_name":"Audio Deepfake Detection"},{"task_slug":"deepfake-detection","task_name":"DeepFake Detection"},{"task_slug":"face-swapping","task_name":"Face Swapping"}],"methods":[],"datasets_introduced":[{"slug":"wavefake","name":"WaveFake","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.02813","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.02813"}},"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/audio-df-ucb/clonedvoicedetection","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rub-syssec/wavefake","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"ran":0,"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":"c2b0efa076bf5fbe","entry":"blur_image","repo":"rub-syssec/wavefake","repo_kind":"official","path":"dfadetect/attribution.py","file_url":"https://github.com/rub-syssec/wavefake/blob/HEAD/dfadetect/attribution.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c2b0efa076bf5fbe"}},{"code_sha256_prefix":"055ad46b81aadbc9","entry":"compute_gradients","repo":"rub-syssec/wavefake","repo_kind":"official","path":"dfadetect/attribution.py","file_url":"https://github.com/rub-syssec/wavefake/blob/HEAD/dfadetect/attribution.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"055ad46b81aadbc9"}},{"code_sha256_prefix":"7d6f13721ee12d25","entry":"feature_kwargs","repo":"rub-syssec/wavefake","repo_kind":"official","path":"experiment_config.py","file_url":"https://github.com/rub-syssec/wavefake/blob/HEAD/experiment_config.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7d6f13721ee12d25"}},{"code_sha256_prefix":"230e65e3fcbee0aa","entry":"find_wav_files","repo":"rub-syssec/wavefake","repo_kind":"official","path":"dfadetect/utils.py","file_url":"https://github.com/rub-syssec/wavefake/blob/HEAD/dfadetect/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"230e65e3fcbee0aa"}},{"code_sha256_prefix":"9112ab69d2ec3a50","entry":"integral_approximation","repo":"rub-syssec/wavefake","repo_kind":"official","path":"dfadetect/attribution.py","file_url":"https://github.com/rub-syssec/wavefake/blob/HEAD/dfadetect/attribution.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9112ab69d2ec3a50"}},{"code_sha256_prefix":"371c6c7eedd45605","entry":"score","repo":"rub-syssec/wavefake","repo_kind":"official","path":"dfadetect/models/gaussian_mixture_model.py","file_url":"https://github.com/rub-syssec/wavefake/blob/HEAD/dfadetect/models/gaussian_mixture_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"371c6c7eedd45605"}},{"code_sha256_prefix":"9edd332fbe6d1e73","entry":"score_batch","repo":"rub-syssec/wavefake","repo_kind":"official","path":"dfadetect/models/gaussian_mixture_model.py","file_url":"https://github.com/rub-syssec/wavefake/blob/HEAD/dfadetect/models/gaussian_mixture_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9edd332fbe6d1e73"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}