{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RHLFLI57PPAPAZ4JWGOSTA7AYD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7f5896f0ef39857d31571c151c5e7d375ff9e20ae0be26341d81d218b86a5739","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-22T13:57:02Z","title_canon_sha256":"c6c96ae72c2feec11853d71647cc2ee2dbfbd298e7569429d23e2394a46464fa"},"schema_version":"1.0","source":{"id":"2505.16691","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16691","created_at":"2026-07-05T11:08:22Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16691v2","created_at":"2026-07-05T11:08:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16691","created_at":"2026-07-05T11:08:22Z"},{"alias_kind":"pith_short_12","alias_value":"RHLFLI57PPAP","created_at":"2026-07-05T11:08:22Z"},{"alias_kind":"pith_short_16","alias_value":"RHLFLI57PPAPAZ4J","created_at":"2026-07-05T11:08:22Z"},{"alias_kind":"pith_short_8","alias_value":"RHLFLI57","created_at":"2026-07-05T11:08:22Z"}],"graph_snapshots":[{"event_id":"sha256:4e7e5771ddaea2baf01ac8771b61c312251d6fcff5f2c1fb962d31284cc6b60f","target":"graph","created_at":"2026-07-05T11:08:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.16691/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Advait Joglekar, Divyanshu Singh, Rooshil Rohit Bhatia, S. Umesh","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-22T13:57:02Z","title":"EZ-VC: Easy Zero-shot Any-to-Any Voice Conversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16691","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:16c6b523aa13f63403bbffede74a00cf8be85395d4813d2831c6a3f746de73f7","target":"record","created_at":"2026-07-05T11:08:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7f5896f0ef39857d31571c151c5e7d375ff9e20ae0be26341d81d218b86a5739","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-22T13:57:02Z","title_canon_sha256":"c6c96ae72c2feec11853d71647cc2ee2dbfbd298e7569429d23e2394a46464fa"},"schema_version":"1.0","source":{"id":"2505.16691","kind":"arxiv","version":2}},"canonical_sha256":"89d655a3bf7bc0f06789b19d2983e0c0f7934fd6e749e502ffe8b1ecfe1b658c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89d655a3bf7bc0f06789b19d2983e0c0f7934fd6e749e502ffe8b1ecfe1b658c","first_computed_at":"2026-07-05T11:08:22.481670Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:22.481670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K/YLngbPdyYj07rPCbBTGdFMOpSSbL8JynIH6EAmDmqO7Z8hUgYTMXv+04E2i39rNN8/4vAkiGeou7gle6OXCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:22.482187Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16691","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16c6b523aa13f63403bbffede74a00cf8be85395d4813d2831c6a3f746de73f7","sha256:4e7e5771ddaea2baf01ac8771b61c312251d6fcff5f2c1fb962d31284cc6b60f"],"state_sha256":"0a68e16a7b7a3088e6f8364b5df3edb52c940252a83fc99d666eed03e8f1cebb"}