{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EAUDONARYQ5XSY2JG7AJ3ZJFO7","short_pith_number":"pith:EAUDONAR","schema_version":"1.0","canonical_sha256":"2028373411c43b79634937c09de52577db9a5885b3d2f349395a7e5749f0efc2","source":{"kind":"arxiv","id":"2409.08913","version":2},"attestation_state":"computed","paper":{"title":"HLTCOE JHU Submission to the Voice Privacy Challenge 2024","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.AS","authors_text":"Ashi Garg, Henry Li Xinyuan, Kevin Duh, Leibny Paola Garc\\'ia-Perera, Matthew Wiesner, Nicholas Andrews, Sanjeev Khudanpur, Zexin Cai","submitted_at":"2024-09-13T15:29:37Z","abstract_excerpt":"We present a number of systems for the Voice Privacy Challenge, including voice conversion based systems such as the kNN-VC method and the WavLM voice Conversion method, and text-to-speech (TTS) based systems including Whisper-VITS. We found that while voice conversion systems better preserve emotional content, they struggle to conceal speaker identity in semi-white-box attack scenarios; conversely, TTS methods perform better at anonymization and worse at emotion preservation. Finally, we propose a random admixture system which seeks to balance out the strengths and weaknesses of the two categ"},"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":"2409.08913","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-13T15:29:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2fb07757a28e0f91df833307528f0258caaea1fd09f3e4ca9e3f5064cd9705b3","abstract_canon_sha256":"e5eb731750da0022543590529c79518f84ce28786d766f91f601c1faa25f47d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:51.568808Z","signature_b64":"g+iZJ1MAZmEVROAGbf7aDJpICrQYfkiI2ltkt16fbfqLEZtzZYG81dNfJRUf72oisusIwB0X9gLntekFV2tEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2028373411c43b79634937c09de52577db9a5885b3d2f349395a7e5749f0efc2","last_reissued_at":"2026-07-05T09:07:51.568308Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:51.568308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HLTCOE JHU Submission to the Voice Privacy Challenge 2024","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.AS","authors_text":"Ashi Garg, Henry Li Xinyuan, Kevin Duh, Leibny Paola Garc\\'ia-Perera, Matthew Wiesner, Nicholas Andrews, Sanjeev Khudanpur, Zexin Cai","submitted_at":"2024-09-13T15:29:37Z","abstract_excerpt":"We present a number of systems for the Voice Privacy Challenge, including voice conversion based systems such as the kNN-VC method and the WavLM voice Conversion method, and text-to-speech (TTS) based systems including Whisper-VITS. We found that while voice conversion systems better preserve emotional content, they struggle to conceal speaker identity in semi-white-box attack scenarios; conversely, TTS methods perform better at anonymization and worse at emotion preservation. Finally, we propose a random admixture system which seeks to balance out the strengths and weaknesses of the two categ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08913","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/2409.08913/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":"2409.08913","created_at":"2026-07-05T09:07:51.568382+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.08913v2","created_at":"2026-07-05T09:07:51.568382+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08913","created_at":"2026-07-05T09:07:51.568382+00:00"},{"alias_kind":"pith_short_12","alias_value":"EAUDONARYQ5X","created_at":"2026-07-05T09:07:51.568382+00:00"},{"alias_kind":"pith_short_16","alias_value":"EAUDONARYQ5XSY2J","created_at":"2026-07-05T09:07:51.568382+00:00"},{"alias_kind":"pith_short_8","alias_value":"EAUDONAR","created_at":"2026-07-05T09:07:51.568382+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00407","citing_title":"Privacy-preserving Prosody Representation Learning","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EAUDONARYQ5XSY2JG7AJ3ZJFO7","json":"https://pith.science/pith/EAUDONARYQ5XSY2JG7AJ3ZJFO7.json","graph_json":"https://pith.science/api/pith-number/EAUDONARYQ5XSY2JG7AJ3ZJFO7/graph.json","events_json":"https://pith.science/api/pith-number/EAUDONARYQ5XSY2JG7AJ3ZJFO7/events.json","paper":"https://pith.science/paper/EAUDONAR"},"agent_actions":{"view_html":"https://pith.science/pith/EAUDONARYQ5XSY2JG7AJ3ZJFO7","download_json":"https://pith.science/pith/EAUDONARYQ5XSY2JG7AJ3ZJFO7.json","view_paper":"https://pith.science/paper/EAUDONAR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.08913&json=true","fetch_graph":"https://pith.science/api/pith-number/EAUDONARYQ5XSY2JG7AJ3ZJFO7/graph.json","fetch_events":"https://pith.science/api/pith-number/EAUDONARYQ5XSY2JG7AJ3ZJFO7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EAUDONARYQ5XSY2JG7AJ3ZJFO7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EAUDONARYQ5XSY2JG7AJ3ZJFO7/action/storage_attestation","attest_author":"https://pith.science/pith/EAUDONARYQ5XSY2JG7AJ3ZJFO7/action/author_attestation","sign_citation":"https://pith.science/pith/EAUDONARYQ5XSY2JG7AJ3ZJFO7/action/citation_signature","submit_replication":"https://pith.science/pith/EAUDONARYQ5XSY2JG7AJ3ZJFO7/action/replication_record"}},"created_at":"2026-07-05T09:07:51.568382+00:00","updated_at":"2026-07-05T09:07:51.568382+00:00"}