{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CPTQAQZHJTBGRDH5FP65S5OM2W","short_pith_number":"pith:CPTQAQZH","schema_version":"1.0","canonical_sha256":"13e70043274cc2688cfd2bfdd975ccd585bdeee9d35a965c949375f0556b2878","source":{"kind":"arxiv","id":"2412.04724","version":2},"attestation_state":"computed","paper":{"title":"StableVC: Style Controllable Zero-Shot Voice Conversion with Conditional Flow Matching","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hongbin Zhou, Jiaohao Ye, Jixun Yao, Lei Xie, Yuguang Yang, Yu Pan, Ziqian Ning","submitted_at":"2024-12-06T02:31:23Z","abstract_excerpt":"Zero-shot voice conversion (VC) aims to transfer the timbre from the source speaker to an arbitrary unseen speaker while preserving the original linguistic content. Despite recent advancements in zero-shot VC using language model-based or diffusion-based approaches, several challenges remain: 1) current approaches primarily focus on adapting timbre from unseen speakers and are unable to transfer style and timbre to different unseen speakers independently; 2) these approaches often suffer from slower inference speeds due to the autoregressive modeling methods or the need for numerous sampling s"},"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":"2412.04724","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-12-06T02:31:23Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"4e19270e0ace2a4de4ecc7ee3d85cfa9cee61f0bbfe801d5cc7374563d287330","abstract_canon_sha256":"770eab2f93d2fee819ed064351d4b200d59db1089f2dbe88c33523f0148da3ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:55.978899Z","signature_b64":"4ofKLWi1b0Z3UTNSveSZtKsL1ASjlzgSx0QF4qtg0ZiCD54XNSEIbZ8ogoRckJo2PAH0Pl4MpGO/Cm62aznzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13e70043274cc2688cfd2bfdd975ccd585bdeee9d35a965c949375f0556b2878","last_reissued_at":"2026-07-05T09:46:55.978354Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:55.978354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StableVC: Style Controllable Zero-Shot Voice Conversion with Conditional Flow Matching","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hongbin Zhou, Jiaohao Ye, Jixun Yao, Lei Xie, Yuguang Yang, Yu Pan, Ziqian Ning","submitted_at":"2024-12-06T02:31:23Z","abstract_excerpt":"Zero-shot voice conversion (VC) aims to transfer the timbre from the source speaker to an arbitrary unseen speaker while preserving the original linguistic content. Despite recent advancements in zero-shot VC using language model-based or diffusion-based approaches, several challenges remain: 1) current approaches primarily focus on adapting timbre from unseen speakers and are unable to transfer style and timbre to different unseen speakers independently; 2) these approaches often suffer from slower inference speeds due to the autoregressive modeling methods or the need for numerous sampling s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04724","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/2412.04724/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":"2412.04724","created_at":"2026-07-05T09:46:55.978427+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04724v2","created_at":"2026-07-05T09:46:55.978427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04724","created_at":"2026-07-05T09:46:55.978427+00:00"},{"alias_kind":"pith_short_12","alias_value":"CPTQAQZHJTBG","created_at":"2026-07-05T09:46:55.978427+00:00"},{"alias_kind":"pith_short_16","alias_value":"CPTQAQZHJTBGRDH5","created_at":"2026-07-05T09:46:55.978427+00:00"},{"alias_kind":"pith_short_8","alias_value":"CPTQAQZH","created_at":"2026-07-05T09:46:55.978427+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.12292","citing_title":"CoSyncDiT: Cognitive Synchronous Diffusion Transformer for Movie Dubbing","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CPTQAQZHJTBGRDH5FP65S5OM2W","json":"https://pith.science/pith/CPTQAQZHJTBGRDH5FP65S5OM2W.json","graph_json":"https://pith.science/api/pith-number/CPTQAQZHJTBGRDH5FP65S5OM2W/graph.json","events_json":"https://pith.science/api/pith-number/CPTQAQZHJTBGRDH5FP65S5OM2W/events.json","paper":"https://pith.science/paper/CPTQAQZH"},"agent_actions":{"view_html":"https://pith.science/pith/CPTQAQZHJTBGRDH5FP65S5OM2W","download_json":"https://pith.science/pith/CPTQAQZHJTBGRDH5FP65S5OM2W.json","view_paper":"https://pith.science/paper/CPTQAQZH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04724&json=true","fetch_graph":"https://pith.science/api/pith-number/CPTQAQZHJTBGRDH5FP65S5OM2W/graph.json","fetch_events":"https://pith.science/api/pith-number/CPTQAQZHJTBGRDH5FP65S5OM2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CPTQAQZHJTBGRDH5FP65S5OM2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CPTQAQZHJTBGRDH5FP65S5OM2W/action/storage_attestation","attest_author":"https://pith.science/pith/CPTQAQZHJTBGRDH5FP65S5OM2W/action/author_attestation","sign_citation":"https://pith.science/pith/CPTQAQZHJTBGRDH5FP65S5OM2W/action/citation_signature","submit_replication":"https://pith.science/pith/CPTQAQZHJTBGRDH5FP65S5OM2W/action/replication_record"}},"created_at":"2026-07-05T09:46:55.978427+00:00","updated_at":"2026-07-05T09:46:55.978427+00:00"}