{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RHLFLI57PPAPAZ4JWGOSTA7AYD","short_pith_number":"pith:RHLFLI57","schema_version":"1.0","canonical_sha256":"89d655a3bf7bc0f06789b19d2983e0c0f7934fd6e749e502ffe8b1ecfe1b658c","source":{"kind":"arxiv","id":"2505.16691","version":2},"attestation_state":"computed","paper":{"title":"EZ-VC: Easy Zero-shot Any-to-Any Voice Conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Advait Joglekar, Divyanshu Singh, Rooshil Rohit Bhatia, S. Umesh","submitted_at":"2025-05-22T13:57:02Z","abstract_excerpt":"Voice Conversion research in recent times has increasingly focused on improving the zero-shot capabilities of existing methods. Despite remarkable advancements, current architectures still tend to struggle in zero-shot cross-lingual settings. They are also often unable to generalize for speakers of unseen languages and accents. In this paper, we adopt a simple yet effective approach that combines discrete speech representations from self-supervised models with a non-autoregressive Diffusion-Transformer based conditional flow matching speech decoder. We show that this architecture allows us to "},"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":"2505.16691","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-22T13:57:02Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"c6c96ae72c2feec11853d71647cc2ee2dbfbd298e7569429d23e2394a46464fa","abstract_canon_sha256":"7f5896f0ef39857d31571c151c5e7d375ff9e20ae0be26341d81d218b86a5739"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:22.482187Z","signature_b64":"K/YLngbPdyYj07rPCbBTGdFMOpSSbL8JynIH6EAmDmqO7Z8hUgYTMXv+04E2i39rNN8/4vAkiGeou7gle6OXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89d655a3bf7bc0f06789b19d2983e0c0f7934fd6e749e502ffe8b1ecfe1b658c","last_reissued_at":"2026-07-05T11:08:22.481670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:22.481670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EZ-VC: Easy Zero-shot Any-to-Any Voice Conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Advait Joglekar, Divyanshu Singh, Rooshil Rohit Bhatia, S. Umesh","submitted_at":"2025-05-22T13:57:02Z","abstract_excerpt":"Voice Conversion research in recent times has increasingly focused on improving the zero-shot capabilities of existing methods. Despite remarkable advancements, current architectures still tend to struggle in zero-shot cross-lingual settings. They are also often unable to generalize for speakers of unseen languages and accents. In this paper, we adopt a simple yet effective approach that combines discrete speech representations from self-supervised models with a non-autoregressive Diffusion-Transformer based conditional flow matching speech decoder. We show that this architecture allows us to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16691","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/2505.16691/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":"2505.16691","created_at":"2026-07-05T11:08:22.481727+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16691v2","created_at":"2026-07-05T11:08:22.481727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16691","created_at":"2026-07-05T11:08:22.481727+00:00"},{"alias_kind":"pith_short_12","alias_value":"RHLFLI57PPAP","created_at":"2026-07-05T11:08:22.481727+00:00"},{"alias_kind":"pith_short_16","alias_value":"RHLFLI57PPAPAZ4J","created_at":"2026-07-05T11:08:22.481727+00:00"},{"alias_kind":"pith_short_8","alias_value":"RHLFLI57","created_at":"2026-07-05T11:08:22.481727+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/RHLFLI57PPAPAZ4JWGOSTA7AYD","json":"https://pith.science/pith/RHLFLI57PPAPAZ4JWGOSTA7AYD.json","graph_json":"https://pith.science/api/pith-number/RHLFLI57PPAPAZ4JWGOSTA7AYD/graph.json","events_json":"https://pith.science/api/pith-number/RHLFLI57PPAPAZ4JWGOSTA7AYD/events.json","paper":"https://pith.science/paper/RHLFLI57"},"agent_actions":{"view_html":"https://pith.science/pith/RHLFLI57PPAPAZ4JWGOSTA7AYD","download_json":"https://pith.science/pith/RHLFLI57PPAPAZ4JWGOSTA7AYD.json","view_paper":"https://pith.science/paper/RHLFLI57","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16691&json=true","fetch_graph":"https://pith.science/api/pith-number/RHLFLI57PPAPAZ4JWGOSTA7AYD/graph.json","fetch_events":"https://pith.science/api/pith-number/RHLFLI57PPAPAZ4JWGOSTA7AYD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RHLFLI57PPAPAZ4JWGOSTA7AYD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RHLFLI57PPAPAZ4JWGOSTA7AYD/action/storage_attestation","attest_author":"https://pith.science/pith/RHLFLI57PPAPAZ4JWGOSTA7AYD/action/author_attestation","sign_citation":"https://pith.science/pith/RHLFLI57PPAPAZ4JWGOSTA7AYD/action/citation_signature","submit_replication":"https://pith.science/pith/RHLFLI57PPAPAZ4JWGOSTA7AYD/action/replication_record"}},"created_at":"2026-07-05T11:08:22.481727+00:00","updated_at":"2026-07-05T11:08:22.481727+00:00"}