{"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/automatic-speaker-verification-spoofing-and","title":"Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation","arxiv_id":"2202.12233","date":"2022-02-24","proceeding":null,"authors":["Hemlata Tak","Massimiliano Todisco","Xin Wang","Jee-weon Jung","Junichi Yamagishi","Nicholas Evans"],"abstract":"The performance of spoofing countermeasure systems depends fundamentally upon the use of sufficiently representative training data. With this usually being limited, current solutions typically lack generalisation to attacks encountered in the wild. Strategies to improve reliability in the face of uncontrolled, unpredictable attacks are hence needed. We report in this paper our efforts to use self-supervised learning in the form of a wav2vec 2.0 front-end with fine tuning. Despite initial base representations being learned using only bona fide data and no spoofed data, we obtain the lowest equal error rates reported in the literature for both the ASVspoof 2021 Logical Access and Deepfake databases. When combined with data augmentation,these results correspond to an improvement of almost 90% relative to our baseline system.","url_abs":"https://arxiv.org/abs/2202.12233v2","url_pdf":"https://arxiv.org/pdf/2202.12233v2.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":"automatic-speaker-verification-spoofing-and","repo_url":"https://github.com/Ashigarg123/ShiftySpeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"automatic-speaker-verification-spoofing-and","repo_url":"https://github.com/liu-tianchi/nes2net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"automatic-speaker-verification-spoofing-and","repo_url":"https://github.com/takhemlata/ssl_anti-spoofing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"audio-deepfake-detection","task_name":"Audio Deepfake Detection"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"deepfake-detection","task_name":"DeepFake Detection"},{"task_slug":"face-swapping","task_name":"Face Swapping"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"speaker-verification","task_name":"Speaker Verification"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-deepfake-detection-on-asvspoof-2021","task":"Audio Deepfake Detection","dataset":"ASVspoof 2021","model":"XLSR+AASIST","rank_in_archive_order":2,"of":8,"metrics":{"21DF EER":"3.69","21LA EER":"1.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2202.12233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.12233"}},"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/Ashigarg123/ShiftySpeech","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/liu-tianchi/nes2net","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/takhemlata/ssl_anti-spoofing","reach":null}],"summary":{"ran_honours":1,"unverified":1},"by_repo_kind":{"listed":{"samples":2,"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":"abdb16a09c4042f4","entry":"evaluate_accuracy","repo":"takhemlata/ssl_anti-spoofing","repo_kind":"listed","path":"main_SSL_LA.py","file_url":"https://github.com/takhemlata/ssl_anti-spoofing/blob/HEAD/main_SSL_LA.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"abdb16a09c4042f4"}},{"code_sha256_prefix":"e920304a7ee16ba1","entry":"train_epoch","repo":"takhemlata/ssl_anti-spoofing","repo_kind":"listed","path":"main_SSL_LA.py","file_url":"https://github.com/takhemlata/ssl_anti-spoofing/blob/HEAD/main_SSL_LA.py","link_basis":"first_harvest_node","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":"e920304a7ee16ba1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}