{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4SLHKW7C3ZZ63P67OSEDHI7G3W","short_pith_number":"pith:4SLHKW7C","schema_version":"1.0","canonical_sha256":"e496755be2de73edbfdf748833a3e6ddb332d5a0caf90b2af3b7648c03704854","source":{"kind":"arxiv","id":"2507.14534","version":4},"attestation_state":"computed","paper":{"title":"Conan: A Chunkwise Online Network for Zero-Shot Adaptive Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Baotong Tian, Yu Zhang, Zhiyao Duan","submitted_at":"2025-07-19T08:32:07Z","abstract_excerpt":"Zero-shot online voice conversion (VC) holds significant promise for real-time communications and entertainment. However, current VC models struggle to preserve semantic fidelity under real-time constraints, deliver natural-sounding conversions, and adapt effectively to unseen speaker characteristics. To address these challenges, we introduce Conan, a chunkwise online zero-shot voice conversion model that preserves the content of the source while matching the voice timbre and styles of reference speech. Conan comprises three core components: 1) a Stream Content Extractor that leverages Emforme"},"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":"2507.14534","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-07-19T08:32:07Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"a8c065f0ac6e124da719ed1fe4ab2a068b803e87640063cb0e71e7ab54fa9516","abstract_canon_sha256":"a7443cfc9d226ceffc02d2b50615ec0ff14a0fdbb99242b12f05ac35f9c0b9e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:03.799792Z","signature_b64":"db8hyJ8+f0DIcUEjeeNSFt4jYyUF9EboTF7ZKRF66JxOuOE1Skx0O93dhV8chHlSWPrXm21kur0/SfP/eNDICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e496755be2de73edbfdf748833a3e6ddb332d5a0caf90b2af3b7648c03704854","last_reissued_at":"2026-07-05T12:02:03.799241Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:03.799241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conan: A Chunkwise Online Network for Zero-Shot Adaptive Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Baotong Tian, Yu Zhang, Zhiyao Duan","submitted_at":"2025-07-19T08:32:07Z","abstract_excerpt":"Zero-shot online voice conversion (VC) holds significant promise for real-time communications and entertainment. However, current VC models struggle to preserve semantic fidelity under real-time constraints, deliver natural-sounding conversions, and adapt effectively to unseen speaker characteristics. To address these challenges, we introduce Conan, a chunkwise online zero-shot voice conversion model that preserves the content of the source while matching the voice timbre and styles of reference speech. Conan comprises three core components: 1) a Stream Content Extractor that leverages Emforme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14534","kind":"arxiv","version":4},"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/2507.14534/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":"2507.14534","created_at":"2026-07-05T12:02:03.799292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.14534v4","created_at":"2026-07-05T12:02:03.799292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14534","created_at":"2026-07-05T12:02:03.799292+00:00"},{"alias_kind":"pith_short_12","alias_value":"4SLHKW7C3ZZ6","created_at":"2026-07-05T12:02:03.799292+00:00"},{"alias_kind":"pith_short_16","alias_value":"4SLHKW7C3ZZ63P67","created_at":"2026-07-05T12:02:03.799292+00:00"},{"alias_kind":"pith_short_8","alias_value":"4SLHKW7C","created_at":"2026-07-05T12:02:03.799292+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30940","citing_title":"Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12456","citing_title":"X-VC: Zero-shot Streaming Voice Conversion in Codec Space","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4SLHKW7C3ZZ63P67OSEDHI7G3W","json":"https://pith.science/pith/4SLHKW7C3ZZ63P67OSEDHI7G3W.json","graph_json":"https://pith.science/api/pith-number/4SLHKW7C3ZZ63P67OSEDHI7G3W/graph.json","events_json":"https://pith.science/api/pith-number/4SLHKW7C3ZZ63P67OSEDHI7G3W/events.json","paper":"https://pith.science/paper/4SLHKW7C"},"agent_actions":{"view_html":"https://pith.science/pith/4SLHKW7C3ZZ63P67OSEDHI7G3W","download_json":"https://pith.science/pith/4SLHKW7C3ZZ63P67OSEDHI7G3W.json","view_paper":"https://pith.science/paper/4SLHKW7C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.14534&json=true","fetch_graph":"https://pith.science/api/pith-number/4SLHKW7C3ZZ63P67OSEDHI7G3W/graph.json","fetch_events":"https://pith.science/api/pith-number/4SLHKW7C3ZZ63P67OSEDHI7G3W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4SLHKW7C3ZZ63P67OSEDHI7G3W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4SLHKW7C3ZZ63P67OSEDHI7G3W/action/storage_attestation","attest_author":"https://pith.science/pith/4SLHKW7C3ZZ63P67OSEDHI7G3W/action/author_attestation","sign_citation":"https://pith.science/pith/4SLHKW7C3ZZ63P67OSEDHI7G3W/action/citation_signature","submit_replication":"https://pith.science/pith/4SLHKW7C3ZZ63P67OSEDHI7G3W/action/replication_record"}},"created_at":"2026-07-05T12:02:03.799292+00:00","updated_at":"2026-07-05T12:02:03.799292+00:00"}