{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FSYC4OQJ3SQJIMDFVE4KSXAAAE","short_pith_number":"pith:FSYC4OQJ","schema_version":"1.0","canonical_sha256":"2cb02e3a09dca0943065a938a95c0001008a999cac886618b7b973bc9f981dbe","source":{"kind":"arxiv","id":"2409.00700","version":1},"attestation_state":"computed","paper":{"title":"Seeing Your Speech Style: A Novel Zero-Shot Identity-Disentanglement Face-based Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Li Liu, Yan Rong","submitted_at":"2024-09-01T11:51:18Z","abstract_excerpt":"Face-based Voice Conversion (FVC) is a novel task that leverages facial images to generate the target speaker's voice style. Previous work has two shortcomings: (1) suffering from obtaining facial embeddings that are well-aligned with the speaker's voice identity information, and (2) inadequacy in decoupling content and speaker identity information from the audio input. To address these issues, we present a novel FVC method, Identity-Disentanglement Face-based Voice Conversion (ID-FaceVC), which overcomes the above two limitations. More precisely, we propose an Identity-Aware Query-based Contr"},"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":"2409.00700","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-01T11:51:18Z","cross_cats_sorted":["cs.AI","cs.CV","eess.AS"],"title_canon_sha256":"0f6bed81896f5908c7471049a0055721b68b53e69924a6b932303bd03043bf88","abstract_canon_sha256":"041d74538327b2c4feb3e75a0bec94e383d2ac6174b18e427c820dea162531c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:03.359521Z","signature_b64":"eDpdLMvqg7MPKYHXrgpCXH6TJzUoSY34HvfA6BlLM94sj0sErYU66cgcB8CLq+oARtpcTlPyk03l8qJGj+83BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cb02e3a09dca0943065a938a95c0001008a999cac886618b7b973bc9f981dbe","last_reissued_at":"2026-07-05T09:03:03.359069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:03.359069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Seeing Your Speech Style: A Novel Zero-Shot Identity-Disentanglement Face-based Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Li Liu, Yan Rong","submitted_at":"2024-09-01T11:51:18Z","abstract_excerpt":"Face-based Voice Conversion (FVC) is a novel task that leverages facial images to generate the target speaker's voice style. Previous work has two shortcomings: (1) suffering from obtaining facial embeddings that are well-aligned with the speaker's voice identity information, and (2) inadequacy in decoupling content and speaker identity information from the audio input. To address these issues, we present a novel FVC method, Identity-Disentanglement Face-based Voice Conversion (ID-FaceVC), which overcomes the above two limitations. More precisely, we propose an Identity-Aware Query-based Contr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00700","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/2409.00700/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":"2409.00700","created_at":"2026-07-05T09:03:03.359129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.00700v1","created_at":"2026-07-05T09:03:03.359129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00700","created_at":"2026-07-05T09:03:03.359129+00:00"},{"alias_kind":"pith_short_12","alias_value":"FSYC4OQJ3SQJ","created_at":"2026-07-05T09:03:03.359129+00:00"},{"alias_kind":"pith_short_16","alias_value":"FSYC4OQJ3SQJIMDF","created_at":"2026-07-05T09:03:03.359129+00:00"},{"alias_kind":"pith_short_8","alias_value":"FSYC4OQJ","created_at":"2026-07-05T09:03:03.359129+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00498","citing_title":"MuteSwap: Visual-informed Silent Video Identity Conversion","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FSYC4OQJ3SQJIMDFVE4KSXAAAE","json":"https://pith.science/pith/FSYC4OQJ3SQJIMDFVE4KSXAAAE.json","graph_json":"https://pith.science/api/pith-number/FSYC4OQJ3SQJIMDFVE4KSXAAAE/graph.json","events_json":"https://pith.science/api/pith-number/FSYC4OQJ3SQJIMDFVE4KSXAAAE/events.json","paper":"https://pith.science/paper/FSYC4OQJ"},"agent_actions":{"view_html":"https://pith.science/pith/FSYC4OQJ3SQJIMDFVE4KSXAAAE","download_json":"https://pith.science/pith/FSYC4OQJ3SQJIMDFVE4KSXAAAE.json","view_paper":"https://pith.science/paper/FSYC4OQJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.00700&json=true","fetch_graph":"https://pith.science/api/pith-number/FSYC4OQJ3SQJIMDFVE4KSXAAAE/graph.json","fetch_events":"https://pith.science/api/pith-number/FSYC4OQJ3SQJIMDFVE4KSXAAAE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FSYC4OQJ3SQJIMDFVE4KSXAAAE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FSYC4OQJ3SQJIMDFVE4KSXAAAE/action/storage_attestation","attest_author":"https://pith.science/pith/FSYC4OQJ3SQJIMDFVE4KSXAAAE/action/author_attestation","sign_citation":"https://pith.science/pith/FSYC4OQJ3SQJIMDFVE4KSXAAAE/action/citation_signature","submit_replication":"https://pith.science/pith/FSYC4OQJ3SQJIMDFVE4KSXAAAE/action/replication_record"}},"created_at":"2026-07-05T09:03:03.359129+00:00","updated_at":"2026-07-05T09:03:03.359129+00:00"}