{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WLVXTXMZH7VDJOVJEXWOX7LA7S","short_pith_number":"pith:WLVXTXMZ","schema_version":"1.0","canonical_sha256":"b2eb79dd993fea34baa925ecebfd60fc944924c7fff54c665411ec38cbd3847a","source":{"kind":"arxiv","id":"2312.08676","version":2},"attestation_state":"computed","paper":{"title":"SEF-VC: Speaker Embedding Free Zero-Shot Voice Conversion with Cross Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Junjie Li, Kai Yu, Xie Chen, Yiwei Guo","submitted_at":"2023-12-14T06:26:55Z","abstract_excerpt":"Zero-shot voice conversion (VC) aims to transfer the source speaker timbre to arbitrary unseen target speaker timbre, while keeping the linguistic content unchanged. Although the voice of generated speech can be controlled by providing the speaker embedding of the target speaker, the speaker similarity still lags behind the ground truth recordings. In this paper, we propose SEF-VC, a speaker embedding free voice conversion model, which is designed to learn and incorporate speaker timbre from reference speech via a powerful position-agnostic cross-attention mechanism, and then reconstruct wavef"},"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":"2312.08676","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-12-14T06:26:55Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"9ec95561f4a1bd0b2fdf39f9a613a4f7b8d3c8e586bbf04c3fc3cf7aff157ff2","abstract_canon_sha256":"ab726baafa98f4ffa0e7c8d1226e031eb5c5bfce77489554f46f294654f4544a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:39:12.144417Z","signature_b64":"XCB6O5+bi0CWQmKXqN2WHyJPBICnkLD2NV0wrFtF2MFjyso1dR6PRJxmMzbdh62vt8TAvuzmxSt+tv3/aQpbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2eb79dd993fea34baa925ecebfd60fc944924c7fff54c665411ec38cbd3847a","last_reissued_at":"2026-07-05T07:39:12.143949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:39:12.143949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEF-VC: Speaker Embedding Free Zero-Shot Voice Conversion with Cross Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Junjie Li, Kai Yu, Xie Chen, Yiwei Guo","submitted_at":"2023-12-14T06:26:55Z","abstract_excerpt":"Zero-shot voice conversion (VC) aims to transfer the source speaker timbre to arbitrary unseen target speaker timbre, while keeping the linguistic content unchanged. Although the voice of generated speech can be controlled by providing the speaker embedding of the target speaker, the speaker similarity still lags behind the ground truth recordings. In this paper, we propose SEF-VC, a speaker embedding free voice conversion model, which is designed to learn and incorporate speaker timbre from reference speech via a powerful position-agnostic cross-attention mechanism, and then reconstruct wavef"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08676","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/2312.08676/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":"2312.08676","created_at":"2026-07-05T07:39:12.143999+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.08676v2","created_at":"2026-07-05T07:39:12.143999+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08676","created_at":"2026-07-05T07:39:12.143999+00:00"},{"alias_kind":"pith_short_12","alias_value":"WLVXTXMZH7VD","created_at":"2026-07-05T07:39:12.143999+00:00"},{"alias_kind":"pith_short_16","alias_value":"WLVXTXMZH7VDJOVJ","created_at":"2026-07-05T07:39:12.143999+00:00"},{"alias_kind":"pith_short_8","alias_value":"WLVXTXMZ","created_at":"2026-07-05T07:39:12.143999+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WLVXTXMZH7VDJOVJEXWOX7LA7S","json":"https://pith.science/pith/WLVXTXMZH7VDJOVJEXWOX7LA7S.json","graph_json":"https://pith.science/api/pith-number/WLVXTXMZH7VDJOVJEXWOX7LA7S/graph.json","events_json":"https://pith.science/api/pith-number/WLVXTXMZH7VDJOVJEXWOX7LA7S/events.json","paper":"https://pith.science/paper/WLVXTXMZ"},"agent_actions":{"view_html":"https://pith.science/pith/WLVXTXMZH7VDJOVJEXWOX7LA7S","download_json":"https://pith.science/pith/WLVXTXMZH7VDJOVJEXWOX7LA7S.json","view_paper":"https://pith.science/paper/WLVXTXMZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.08676&json=true","fetch_graph":"https://pith.science/api/pith-number/WLVXTXMZH7VDJOVJEXWOX7LA7S/graph.json","fetch_events":"https://pith.science/api/pith-number/WLVXTXMZH7VDJOVJEXWOX7LA7S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WLVXTXMZH7VDJOVJEXWOX7LA7S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WLVXTXMZH7VDJOVJEXWOX7LA7S/action/storage_attestation","attest_author":"https://pith.science/pith/WLVXTXMZH7VDJOVJEXWOX7LA7S/action/author_attestation","sign_citation":"https://pith.science/pith/WLVXTXMZH7VDJOVJEXWOX7LA7S/action/citation_signature","submit_replication":"https://pith.science/pith/WLVXTXMZH7VDJOVJEXWOX7LA7S/action/replication_record"}},"created_at":"2026-07-05T07:39:12.143999+00:00","updated_at":"2026-07-05T07:39:12.143999+00:00"}