{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QVUVDA5HZ5SS572W2JPFV5NWRG","short_pith_number":"pith:QVUVDA5H","schema_version":"1.0","canonical_sha256":"85695183a7cf652eff56d25e5af5b689bfe9b170c0e35336a08dd8712a865efb","source":{"kind":"arxiv","id":"2506.01014","version":1},"attestation_state":"computed","paper":{"title":"Rhythm Controllable and Efficient Zero-Shot Voice Conversion via Shortcut Flow Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chen Feiyang, Jialong Zuo, Minghui Fang, Mingze Li, Shengpeng Ji, Xiaoda Yang, Xinyu Duan, Xize Cheng, Zhou Zhao, Ziyue Jiang","submitted_at":"2025-06-01T13:53:28Z","abstract_excerpt":"Zero-Shot Voice Conversion (VC) aims to transform the source speaker's timbre into an arbitrary unseen one while retaining speech content. Most prior work focuses on preserving the source's prosody, while fine-grained timbre information may leak through prosody, and transferring target prosody to synthesized speech is rarely studied. In light of this, we propose R-VC, a rhythm-controllable and efficient zero-shot voice conversion model. R-VC employs data perturbation techniques and discretize source speech into Hubert content tokens, eliminating much content-irrelevant information. By leveragi"},"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":"2506.01014","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-01T13:53:28Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"896a864ad8b4961d366f7aa83f1881f668c26410bd0d66dd7bb54c3fd992a1bb","abstract_canon_sha256":"3af5b7a58530442e742c6b259daf1941b17e3441ce8c8cc418ddeddfbec46fa4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:44.537732Z","signature_b64":"0z5VvaI24KICub8FF+SaVIYKPGKq2rE5rf6YMxa7oyrJJMNcdpiLO4AnSVMf/E7IvKG1LbyuJskY2S9lkFjRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85695183a7cf652eff56d25e5af5b689bfe9b170c0e35336a08dd8712a865efb","last_reissued_at":"2026-07-05T11:13:44.537235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:44.537235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rhythm Controllable and Efficient Zero-Shot Voice Conversion via Shortcut Flow Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chen Feiyang, Jialong Zuo, Minghui Fang, Mingze Li, Shengpeng Ji, Xiaoda Yang, Xinyu Duan, Xize Cheng, Zhou Zhao, Ziyue Jiang","submitted_at":"2025-06-01T13:53:28Z","abstract_excerpt":"Zero-Shot Voice Conversion (VC) aims to transform the source speaker's timbre into an arbitrary unseen one while retaining speech content. Most prior work focuses on preserving the source's prosody, while fine-grained timbre information may leak through prosody, and transferring target prosody to synthesized speech is rarely studied. In light of this, we propose R-VC, a rhythm-controllable and efficient zero-shot voice conversion model. R-VC employs data perturbation techniques and discretize source speech into Hubert content tokens, eliminating much content-irrelevant information. By leveragi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01014","kind":"arxiv","version":1},"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/2506.01014/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":"2506.01014","created_at":"2026-07-05T11:13:44.537293+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01014v1","created_at":"2026-07-05T11:13:44.537293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01014","created_at":"2026-07-05T11:13:44.537293+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVUVDA5HZ5SS","created_at":"2026-07-05T11:13:44.537293+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVUVDA5HZ5SS572W","created_at":"2026-07-05T11:13:44.537293+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVUVDA5H","created_at":"2026-07-05T11:13:44.537293+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/QVUVDA5HZ5SS572W2JPFV5NWRG","json":"https://pith.science/pith/QVUVDA5HZ5SS572W2JPFV5NWRG.json","graph_json":"https://pith.science/api/pith-number/QVUVDA5HZ5SS572W2JPFV5NWRG/graph.json","events_json":"https://pith.science/api/pith-number/QVUVDA5HZ5SS572W2JPFV5NWRG/events.json","paper":"https://pith.science/paper/QVUVDA5H"},"agent_actions":{"view_html":"https://pith.science/pith/QVUVDA5HZ5SS572W2JPFV5NWRG","download_json":"https://pith.science/pith/QVUVDA5HZ5SS572W2JPFV5NWRG.json","view_paper":"https://pith.science/paper/QVUVDA5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01014&json=true","fetch_graph":"https://pith.science/api/pith-number/QVUVDA5HZ5SS572W2JPFV5NWRG/graph.json","fetch_events":"https://pith.science/api/pith-number/QVUVDA5HZ5SS572W2JPFV5NWRG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVUVDA5HZ5SS572W2JPFV5NWRG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVUVDA5HZ5SS572W2JPFV5NWRG/action/storage_attestation","attest_author":"https://pith.science/pith/QVUVDA5HZ5SS572W2JPFV5NWRG/action/author_attestation","sign_citation":"https://pith.science/pith/QVUVDA5HZ5SS572W2JPFV5NWRG/action/citation_signature","submit_replication":"https://pith.science/pith/QVUVDA5HZ5SS572W2JPFV5NWRG/action/replication_record"}},"created_at":"2026-07-05T11:13:44.537293+00:00","updated_at":"2026-07-05T11:13:44.537293+00:00"}