{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IMK3BVEDZNPFFFPUOG35JMMSLX","short_pith_number":"pith:IMK3BVED","schema_version":"1.0","canonical_sha256":"4315b0d483cb5e5295f471b7d4b1925df996c48b429ac06c585e21c286feffb0","source":{"kind":"arxiv","id":"2506.01032","version":1},"attestation_state":"computed","paper":{"title":"ReFlow-VC: Zero-shot Voice Conversion Based on Rectified Flow and Speaker Feature Optimization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Kaidi Wang, Lin Li, Peijie Chen, Pengyu Ren, Qingyang Hong, Wenhao Guan","submitted_at":"2025-06-01T14:21:07Z","abstract_excerpt":"In recent years, diffusion-based generative models have demonstrated remarkable performance in speech conversion, including Denoising Diffusion Probabilistic Models (DDPM) and others. However, the advantages of these models come at the cost of requiring a large number of sampling steps. This limitation hinders their practical application in real-world scenarios. In this paper, we introduce ReFlow-VC, a novel high-fidelity speech conversion method based on rectified flow. Specifically, ReFlow-VC is an Ordinary Differential Equation (ODE) model that transforms a Gaussian distribution to the true"},"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":"2506.01032","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-01T14:21:07Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"428080afcc576320f66ff9b091fddcb912c1b199cda1a31f055556e77dacc891","abstract_canon_sha256":"db3c9a137a57e81ada78bfd66a09e8f378ad21aa3f02c803a0fc1cc1cd82a27f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:44.850153Z","signature_b64":"Wp9op5dmhS0iMI1Osv0wTZbctlONlxaf8Gga5QFeGIqJ9TbuVOWbB/nGk4X63Z4R1DhtiOyPbVn1oJUwn/MuDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4315b0d483cb5e5295f471b7d4b1925df996c48b429ac06c585e21c286feffb0","last_reissued_at":"2026-07-05T11:13:44.849698Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:44.849698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReFlow-VC: Zero-shot Voice Conversion Based on Rectified Flow and Speaker Feature Optimization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Kaidi Wang, Lin Li, Peijie Chen, Pengyu Ren, Qingyang Hong, Wenhao Guan","submitted_at":"2025-06-01T14:21:07Z","abstract_excerpt":"In recent years, diffusion-based generative models have demonstrated remarkable performance in speech conversion, including Denoising Diffusion Probabilistic Models (DDPM) and others. However, the advantages of these models come at the cost of requiring a large number of sampling steps. This limitation hinders their practical application in real-world scenarios. In this paper, we introduce ReFlow-VC, a novel high-fidelity speech conversion method based on rectified flow. Specifically, ReFlow-VC is an Ordinary Differential Equation (ODE) model that transforms a Gaussian distribution to the true"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01032","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/2506.01032/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":"2506.01032","created_at":"2026-07-05T11:13:44.849755+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01032v1","created_at":"2026-07-05T11:13:44.849755+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01032","created_at":"2026-07-05T11:13:44.849755+00:00"},{"alias_kind":"pith_short_12","alias_value":"IMK3BVEDZNPF","created_at":"2026-07-05T11:13:44.849755+00:00"},{"alias_kind":"pith_short_16","alias_value":"IMK3BVEDZNPFFFPU","created_at":"2026-07-05T11:13:44.849755+00:00"},{"alias_kind":"pith_short_8","alias_value":"IMK3BVED","created_at":"2026-07-05T11:13:44.849755+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01032","citing_title":"ReFlow-VC: Zero-shot Voice Conversion Based on Rectified Flow and Speaker Feature Optimization","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IMK3BVEDZNPFFFPUOG35JMMSLX","json":"https://pith.science/pith/IMK3BVEDZNPFFFPUOG35JMMSLX.json","graph_json":"https://pith.science/api/pith-number/IMK3BVEDZNPFFFPUOG35JMMSLX/graph.json","events_json":"https://pith.science/api/pith-number/IMK3BVEDZNPFFFPUOG35JMMSLX/events.json","paper":"https://pith.science/paper/IMK3BVED"},"agent_actions":{"view_html":"https://pith.science/pith/IMK3BVEDZNPFFFPUOG35JMMSLX","download_json":"https://pith.science/pith/IMK3BVEDZNPFFFPUOG35JMMSLX.json","view_paper":"https://pith.science/paper/IMK3BVED","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01032&json=true","fetch_graph":"https://pith.science/api/pith-number/IMK3BVEDZNPFFFPUOG35JMMSLX/graph.json","fetch_events":"https://pith.science/api/pith-number/IMK3BVEDZNPFFFPUOG35JMMSLX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IMK3BVEDZNPFFFPUOG35JMMSLX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IMK3BVEDZNPFFFPUOG35JMMSLX/action/storage_attestation","attest_author":"https://pith.science/pith/IMK3BVEDZNPFFFPUOG35JMMSLX/action/author_attestation","sign_citation":"https://pith.science/pith/IMK3BVEDZNPFFFPUOG35JMMSLX/action/citation_signature","submit_replication":"https://pith.science/pith/IMK3BVEDZNPFFFPUOG35JMMSLX/action/replication_record"}},"created_at":"2026-07-05T11:13:44.849755+00:00","updated_at":"2026-07-05T11:13:44.849755+00:00"}