{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BHLWW5DOB2KWJA2US7ULYALY6J","short_pith_number":"pith:BHLWW5DO","schema_version":"1.0","canonical_sha256":"09d76b746e0e9564835497e8bc0178f2564ec70e28013ccdb1c90ab3d7903000","source":{"kind":"arxiv","id":"2601.18094","version":2},"attestation_state":"computed","paper":{"title":"OneVoice: One Model, Triple Scenarios-Towards Unified Zero-shot Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Junlan Feng, Shilei Zhang, Tao Li, Wenshuo Ge, Zhichao Wang, Zihao Cui","submitted_at":"2026-01-26T03:11:56Z","abstract_excerpt":"Recent progress of voice conversion~(VC) has achieved a new milestone in speaker cloning and linguistic preservation. But the field remains fragmented, relying on specialized models for linguistic-preserving, expressive, and singing scenarios. We propose OneVoice, a unified zero-shot framework capable of handling all three scenarios within a single model. OneVoice is built upon a continuous language model trained with VAE-free next-patch diffusion, ensuring high fidelity and efficient sequence modeling. Its core design for unification lies in a Mixture-of-Experts (MoE) designed to explicitly m"},"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":"2601.18094","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-01-26T03:11:56Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"4ac04189d2dede5bf21db264d123bf6ad473b5c19c41335781463326a9ab27b6","abstract_canon_sha256":"c4237cbf86d23720f0adb3d458f2ff2767a437b679124865f406982648e7bd3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:54.582289Z","signature_b64":"tR5jA2beKrs9nuaw6WwqO1A2VVUI71ToxXTl167h298ZBVmgaUTz8ELH2U+p4GYMn2P3Al2rA6TkoXNIf94WCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09d76b746e0e9564835497e8bc0178f2564ec70e28013ccdb1c90ab3d7903000","last_reissued_at":"2026-05-22T01:03:54.581472Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:54.581472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OneVoice: One Model, Triple Scenarios-Towards Unified Zero-shot Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Junlan Feng, Shilei Zhang, Tao Li, Wenshuo Ge, Zhichao Wang, Zihao Cui","submitted_at":"2026-01-26T03:11:56Z","abstract_excerpt":"Recent progress of voice conversion~(VC) has achieved a new milestone in speaker cloning and linguistic preservation. But the field remains fragmented, relying on specialized models for linguistic-preserving, expressive, and singing scenarios. We propose OneVoice, a unified zero-shot framework capable of handling all three scenarios within a single model. OneVoice is built upon a continuous language model trained with VAE-free next-patch diffusion, ensuring high fidelity and efficient sequence modeling. Its core design for unification lies in a Mixture-of-Experts (MoE) designed to explicitly m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.18094","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/2601.18094/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":"2601.18094","created_at":"2026-05-22T01:03:54.581591+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.18094v2","created_at":"2026-05-22T01:03:54.581591+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.18094","created_at":"2026-05-22T01:03:54.581591+00:00"},{"alias_kind":"pith_short_12","alias_value":"BHLWW5DOB2KW","created_at":"2026-05-22T01:03:54.581591+00:00"},{"alias_kind":"pith_short_16","alias_value":"BHLWW5DOB2KWJA2U","created_at":"2026-05-22T01:03:54.581591+00:00"},{"alias_kind":"pith_short_8","alias_value":"BHLWW5DO","created_at":"2026-05-22T01:03:54.581591+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/BHLWW5DOB2KWJA2US7ULYALY6J","json":"https://pith.science/pith/BHLWW5DOB2KWJA2US7ULYALY6J.json","graph_json":"https://pith.science/api/pith-number/BHLWW5DOB2KWJA2US7ULYALY6J/graph.json","events_json":"https://pith.science/api/pith-number/BHLWW5DOB2KWJA2US7ULYALY6J/events.json","paper":"https://pith.science/paper/BHLWW5DO"},"agent_actions":{"view_html":"https://pith.science/pith/BHLWW5DOB2KWJA2US7ULYALY6J","download_json":"https://pith.science/pith/BHLWW5DOB2KWJA2US7ULYALY6J.json","view_paper":"https://pith.science/paper/BHLWW5DO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.18094&json=true","fetch_graph":"https://pith.science/api/pith-number/BHLWW5DOB2KWJA2US7ULYALY6J/graph.json","fetch_events":"https://pith.science/api/pith-number/BHLWW5DOB2KWJA2US7ULYALY6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BHLWW5DOB2KWJA2US7ULYALY6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BHLWW5DOB2KWJA2US7ULYALY6J/action/storage_attestation","attest_author":"https://pith.science/pith/BHLWW5DOB2KWJA2US7ULYALY6J/action/author_attestation","sign_citation":"https://pith.science/pith/BHLWW5DOB2KWJA2US7ULYALY6J/action/citation_signature","submit_replication":"https://pith.science/pith/BHLWW5DOB2KWJA2US7ULYALY6J/action/replication_record"}},"created_at":"2026-05-22T01:03:54.581591+00:00","updated_at":"2026-05-22T01:03:54.581591+00:00"}