{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6OM6YNBGJVWV4D3W6OSZYYADSR","short_pith_number":"pith:6OM6YNBG","schema_version":"1.0","canonical_sha256":"f399ec34264d6d5e0f76f3a59c6003945f664f310db3faa360e726063de0360b","source":{"kind":"arxiv","id":"2404.00809","version":1},"attestation_state":"computed","paper":{"title":"Heterogeneity over Homogeneity: Investigating Multilingual Speech Pre-Trained Models for Detecting Audio Deepfake","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Arun Balaji Buduru, Gautam Siddharth Kashyap, Orchid Chetia Phukan, Rajesh Sharma","submitted_at":"2024-03-31T21:48:50Z","abstract_excerpt":"In this work, we investigate multilingual speech Pre-Trained models (PTMs) for Audio deepfake detection (ADD). We hypothesize that multilingual PTMs trained on large-scale diverse multilingual data gain knowledge about diverse pitches, accents, and tones, during their pre-training phase and making them more robust to variations. As a result, they will be more effective for detecting audio deepfakes. To validate our hypothesis, we extract representations from state-of-the-art (SOTA) PTMs including monolingual, multilingual as well as PTMs trained for speaker and emotion recognition, and evaluat"},"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":"2404.00809","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-03-31T21:48:50Z","cross_cats_sorted":[],"title_canon_sha256":"5653e73137c1b32dfd5be83d2a293bd4e41437e58d4158b859ecd87eefa742be","abstract_canon_sha256":"3f53b34dbe4f3b95d8feb90f521d129292072d3cf41c452118b7f327dda5e42a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:56.991766Z","signature_b64":"CQMlGYOqMA+QLnv1lQ1WNGAVP7UZiF3LAQQy77NIWdu7SblctjNaOjoN33I9qyyYbOofsiayKUiv6oZZ1qxbBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f399ec34264d6d5e0f76f3a59c6003945f664f310db3faa360e726063de0360b","last_reissued_at":"2026-07-05T08:02:56.991297Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:56.991297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heterogeneity over Homogeneity: Investigating Multilingual Speech Pre-Trained Models for Detecting Audio Deepfake","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Arun Balaji Buduru, Gautam Siddharth Kashyap, Orchid Chetia Phukan, Rajesh Sharma","submitted_at":"2024-03-31T21:48:50Z","abstract_excerpt":"In this work, we investigate multilingual speech Pre-Trained models (PTMs) for Audio deepfake detection (ADD). We hypothesize that multilingual PTMs trained on large-scale diverse multilingual data gain knowledge about diverse pitches, accents, and tones, during their pre-training phase and making them more robust to variations. As a result, they will be more effective for detecting audio deepfakes. To validate our hypothesis, we extract representations from state-of-the-art (SOTA) PTMs including monolingual, multilingual as well as PTMs trained for speaker and emotion recognition, and evaluat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00809","kind":"arxiv","version":1},"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/2404.00809/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":"2404.00809","created_at":"2026-07-05T08:02:56.991345+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.00809v1","created_at":"2026-07-05T08:02:56.991345+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00809","created_at":"2026-07-05T08:02:56.991345+00:00"},{"alias_kind":"pith_short_12","alias_value":"6OM6YNBGJVWV","created_at":"2026-07-05T08:02:56.991345+00:00"},{"alias_kind":"pith_short_16","alias_value":"6OM6YNBGJVWV4D3W","created_at":"2026-07-05T08:02:56.991345+00:00"},{"alias_kind":"pith_short_8","alias_value":"6OM6YNBG","created_at":"2026-07-05T08:02:56.991345+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21735","citing_title":"Bridging the Age Gap: Towards Detecting Neural Audio Codec Synthesized Elderly Speech Deepfake","ref_index":38,"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":113,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6OM6YNBGJVWV4D3W6OSZYYADSR","json":"https://pith.science/pith/6OM6YNBGJVWV4D3W6OSZYYADSR.json","graph_json":"https://pith.science/api/pith-number/6OM6YNBGJVWV4D3W6OSZYYADSR/graph.json","events_json":"https://pith.science/api/pith-number/6OM6YNBGJVWV4D3W6OSZYYADSR/events.json","paper":"https://pith.science/paper/6OM6YNBG"},"agent_actions":{"view_html":"https://pith.science/pith/6OM6YNBGJVWV4D3W6OSZYYADSR","download_json":"https://pith.science/pith/6OM6YNBGJVWV4D3W6OSZYYADSR.json","view_paper":"https://pith.science/paper/6OM6YNBG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.00809&json=true","fetch_graph":"https://pith.science/api/pith-number/6OM6YNBGJVWV4D3W6OSZYYADSR/graph.json","fetch_events":"https://pith.science/api/pith-number/6OM6YNBGJVWV4D3W6OSZYYADSR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6OM6YNBGJVWV4D3W6OSZYYADSR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6OM6YNBGJVWV4D3W6OSZYYADSR/action/storage_attestation","attest_author":"https://pith.science/pith/6OM6YNBGJVWV4D3W6OSZYYADSR/action/author_attestation","sign_citation":"https://pith.science/pith/6OM6YNBGJVWV4D3W6OSZYYADSR/action/citation_signature","submit_replication":"https://pith.science/pith/6OM6YNBGJVWV4D3W6OSZYYADSR/action/replication_record"}},"created_at":"2026-07-05T08:02:56.991345+00:00","updated_at":"2026-07-05T08:02:56.991345+00:00"}