{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FZKXDZJ7UGPLHFNRTDTDN7N27C","short_pith_number":"pith:FZKXDZJ7","schema_version":"1.0","canonical_sha256":"2e5571e53fa19eb395b198e636fdbaf894d703b75513d975c33652ca8318f650","source":{"kind":"arxiv","id":"2202.12233","version":2},"attestation_state":"computed","paper":{"title":"Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hemlata Tak, Jee-weon Jung, Junichi Yamagishi, Massimiliano Todisco, Nicholas Evans, Xin Wang","submitted_at":"2022-02-24T17:55:00Z","abstract_excerpt":"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 equa"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2202.12233","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-02-24T17:55:00Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"b6bb0ab2163965d8c0498451d2c13ab3c4b71b9b5ef7130f1acafc23ae02b372","abstract_canon_sha256":"09acbc9c73f93593e270bdd3af95bd8e0ad9fad2f3c59309695aa4928622a0c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:00:23.685976Z","signature_b64":"NLTZyyr1iXckcgt+OlUH1ZPSpGCrCr9PXDxIaYMs7AE/CwBjFgq5m7ZJ+xslPRuJ/Yvax8pYLdr/exrO1SDdBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e5571e53fa19eb395b198e636fdbaf894d703b75513d975c33652ca8318f650","last_reissued_at":"2026-07-05T04:00:23.685487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:00:23.685487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hemlata Tak, Jee-weon Jung, Junichi Yamagishi, Massimiliano Todisco, Nicholas Evans, Xin Wang","submitted_at":"2022-02-24T17:55:00Z","abstract_excerpt":"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 equa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.12233","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2202.12233/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2202.12233","created_at":"2026-07-05T04:00:23.685545+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.12233v2","created_at":"2026-07-05T04:00:23.685545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.12233","created_at":"2026-07-05T04:00:23.685545+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZKXDZJ7UGPL","created_at":"2026-07-05T04:00:23.685545+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZKXDZJ7UGPLHFNR","created_at":"2026-07-05T04:00:23.685545+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZKXDZJ7","created_at":"2026-07-05T04:00:23.685545+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10223","citing_title":"Dual-Branch Gated Fusion for Open-Set Audio Deepfake Source Tracing","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30780","citing_title":"Detecting Audio Deepfakes on the Edge:Lightweight SSL-Based Detection in a Browser Plugin","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30366","citing_title":"Escaping the Linearity Trap: Manifold Detours for Black-Box Adversarial Attacks on Singing Audio Deepfake Detection","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2401.09512","citing_title":"MLAAD: The Multi-Language Audio Anti-Spoofing Dataset","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2504.12423","citing_title":"Benchmarking Audio Deepfake Detection Robustness in Real-world Communication Scenarios","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17737","citing_title":"Profiling the Voice: Speaker-Specific Phoneme Fingerprinting for Speech Deepfake Detection","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24674","citing_title":"Advancing Zero-Shot Open-Set Speech Deepfake Source Tracing","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26057","citing_title":"Similarity Choice and Negative Scaling in Supervised Contrastive Learning for Deepfake Audio Detection","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02223","citing_title":"Toward Fine-Grained Speech Inpainting Forensics:A Dataset, Method, and Metric for Multi-Region Tampering Localization","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23957","citing_title":"LAVA: Layered Audio-Visual Anti-tampering Watermarking for Robust Deepfake Detection and Localization","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01638","citing_title":"Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13229","citing_title":"ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19949","citing_title":"Indic-CodecFake meets SATYAM: Towards Detecting Neural Audio Codec Synthesized Speech Deepfakes in Indic Languages","ref_index":148,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FZKXDZJ7UGPLHFNRTDTDN7N27C","json":"https://pith.science/pith/FZKXDZJ7UGPLHFNRTDTDN7N27C.json","graph_json":"https://pith.science/api/pith-number/FZKXDZJ7UGPLHFNRTDTDN7N27C/graph.json","events_json":"https://pith.science/api/pith-number/FZKXDZJ7UGPLHFNRTDTDN7N27C/events.json","paper":"https://pith.science/paper/FZKXDZJ7"},"agent_actions":{"view_html":"https://pith.science/pith/FZKXDZJ7UGPLHFNRTDTDN7N27C","download_json":"https://pith.science/pith/FZKXDZJ7UGPLHFNRTDTDN7N27C.json","view_paper":"https://pith.science/paper/FZKXDZJ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.12233&json=true","fetch_graph":"https://pith.science/api/pith-number/FZKXDZJ7UGPLHFNRTDTDN7N27C/graph.json","fetch_events":"https://pith.science/api/pith-number/FZKXDZJ7UGPLHFNRTDTDN7N27C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZKXDZJ7UGPLHFNRTDTDN7N27C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZKXDZJ7UGPLHFNRTDTDN7N27C/action/storage_attestation","attest_author":"https://pith.science/pith/FZKXDZJ7UGPLHFNRTDTDN7N27C/action/author_attestation","sign_citation":"https://pith.science/pith/FZKXDZJ7UGPLHFNRTDTDN7N27C/action/citation_signature","submit_replication":"https://pith.science/pith/FZKXDZJ7UGPLHFNRTDTDN7N27C/action/replication_record"}},"created_at":"2026-07-05T04:00:23.685545+00:00","updated_at":"2026-07-05T04:00:23.685545+00:00"}