{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZY5CCQVYZP2MLCCFXCILOSVH4O","short_pith_number":"pith:ZY5CCQVY","schema_version":"1.0","canonical_sha256":"ce3a2142b8cbf4c58845b890b74aa7e38f214d7ac4ec214eeec78f0e090455f0","source":{"kind":"arxiv","id":"2411.16147","version":2},"attestation_state":"computed","paper":{"title":"QR-VC: Leveraging Quantization Residuals for Linear Disentanglement in Zero-Shot Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jinsung Yoon, Wooyeol Jeong, Young-Joo Suh, Youngjun Sim","submitted_at":"2024-11-25T07:14:26Z","abstract_excerpt":"Zero-shot voice conversion is a technique that alters the speaker identity of an input speech to match a target speaker using only a single reference utterance, without requiring additional training. Recent approaches extensively utilize self-supervised learning features with K-means quantization to extract high-quality content representations while removing speaker identity. However, this quantization process also eliminates fine-grained phonetic and prosodic variations, degrading intelligibility and prosody preservation. While prior works have primarily focused on quantized representations, "},"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":"2411.16147","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-11-25T07:14:26Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"e7bd53a7074d232ba7a63366b64027c2d5b4feaaba67d1273994ab0eedf5f2e7","abstract_canon_sha256":"27486c95b37e9723db0790afcabd6c2ba567836b1c26c73db4c288a68df3820a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:56.555203Z","signature_b64":"S5jw+9crR7gY2LwLSHlyzTXnK6poNWXsdtwl1bSZiFJ8KCaybPpXrBnQnaW4FO0T0mpjEfzpB5KcIFiJVyNFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce3a2142b8cbf4c58845b890b74aa7e38f214d7ac4ec214eeec78f0e090455f0","last_reissued_at":"2026-07-05T12:07:56.554564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:56.554564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QR-VC: Leveraging Quantization Residuals for Linear Disentanglement in Zero-Shot Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jinsung Yoon, Wooyeol Jeong, Young-Joo Suh, Youngjun Sim","submitted_at":"2024-11-25T07:14:26Z","abstract_excerpt":"Zero-shot voice conversion is a technique that alters the speaker identity of an input speech to match a target speaker using only a single reference utterance, without requiring additional training. Recent approaches extensively utilize self-supervised learning features with K-means quantization to extract high-quality content representations while removing speaker identity. However, this quantization process also eliminates fine-grained phonetic and prosodic variations, degrading intelligibility and prosody preservation. While prior works have primarily focused on quantized representations, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16147","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/2411.16147/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":"2411.16147","created_at":"2026-07-05T12:07:56.554628+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16147v2","created_at":"2026-07-05T12:07:56.554628+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16147","created_at":"2026-07-05T12:07:56.554628+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZY5CCQVYZP2M","created_at":"2026-07-05T12:07:56.554628+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZY5CCQVYZP2MLCCF","created_at":"2026-07-05T12:07:56.554628+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZY5CCQVY","created_at":"2026-07-05T12:07:56.554628+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.04996","citing_title":"REF-VC: Robust, Expressive and Fast Zero-Shot Voice Conversion with Diffusion Transformers","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZY5CCQVYZP2MLCCFXCILOSVH4O","json":"https://pith.science/pith/ZY5CCQVYZP2MLCCFXCILOSVH4O.json","graph_json":"https://pith.science/api/pith-number/ZY5CCQVYZP2MLCCFXCILOSVH4O/graph.json","events_json":"https://pith.science/api/pith-number/ZY5CCQVYZP2MLCCFXCILOSVH4O/events.json","paper":"https://pith.science/paper/ZY5CCQVY"},"agent_actions":{"view_html":"https://pith.science/pith/ZY5CCQVYZP2MLCCFXCILOSVH4O","download_json":"https://pith.science/pith/ZY5CCQVYZP2MLCCFXCILOSVH4O.json","view_paper":"https://pith.science/paper/ZY5CCQVY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16147&json=true","fetch_graph":"https://pith.science/api/pith-number/ZY5CCQVYZP2MLCCFXCILOSVH4O/graph.json","fetch_events":"https://pith.science/api/pith-number/ZY5CCQVYZP2MLCCFXCILOSVH4O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZY5CCQVYZP2MLCCFXCILOSVH4O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZY5CCQVYZP2MLCCFXCILOSVH4O/action/storage_attestation","attest_author":"https://pith.science/pith/ZY5CCQVYZP2MLCCFXCILOSVH4O/action/author_attestation","sign_citation":"https://pith.science/pith/ZY5CCQVYZP2MLCCFXCILOSVH4O/action/citation_signature","submit_replication":"https://pith.science/pith/ZY5CCQVYZP2MLCCFXCILOSVH4O/action/replication_record"}},"created_at":"2026-07-05T12:07:56.554628+00:00","updated_at":"2026-07-05T12:07:56.554628+00:00"}