{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z633BMNEQOU2I5ZKCWFTI2UKMA","short_pith_number":"pith:Z633BMNE","schema_version":"1.0","canonical_sha256":"cfb7b0b1a483a9a4772a158b346a8a60036b53d59b0f4d5c6aae95c45ddb7764","source":{"kind":"arxiv","id":"2506.09709","version":1},"attestation_state":"computed","paper":{"title":"Training-Free Voice Conversion with Factorized Optimal Transport","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alexander Lobashev, Assel Yermekova, Maria Larchenko","submitted_at":"2025-06-11T13:23:03Z","abstract_excerpt":"This paper introduces Factorized MKL-VC, a training-free modification for kNN-VC pipeline. In contrast with original pipeline, our algorithm performs high quality any-to-any cross-lingual voice conversion with only 5 second of reference audio. MKL-VC replaces kNN regression with a factorized optimal transport map in WavLM embedding subspaces, derived from Monge-Kantorovich Linear solution. Factorization addresses non-uniform variance across dimensions, ensuring effective feature transformation. Experiments on LibriSpeech and FLEURS datasets show MKL-VC significantly improves content preservati"},"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":"2506.09709","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-11T13:23:03Z","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"title_canon_sha256":"292920c77e208832405cf73c28887d58a9f859bc60a7b63392321b4f073d2d10","abstract_canon_sha256":"debcb471ba474c4c3053f23c32eef0d39458e2dc4c47bce419c21fe0d9c53608"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:55.660138Z","signature_b64":"MQmRTVDxzY769mHhZs8542vMHD5zmKNwZrMT7nJJ0d7GU/L0px90F7vUmtbu/n90Sc9SPBUEY4v11012O286Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfb7b0b1a483a9a4772a158b346a8a60036b53d59b0f4d5c6aae95c45ddb7764","last_reissued_at":"2026-07-05T11:19:55.659604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:55.659604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training-Free Voice Conversion with Factorized Optimal Transport","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alexander Lobashev, Assel Yermekova, Maria Larchenko","submitted_at":"2025-06-11T13:23:03Z","abstract_excerpt":"This paper introduces Factorized MKL-VC, a training-free modification for kNN-VC pipeline. In contrast with original pipeline, our algorithm performs high quality any-to-any cross-lingual voice conversion with only 5 second of reference audio. MKL-VC replaces kNN regression with a factorized optimal transport map in WavLM embedding subspaces, derived from Monge-Kantorovich Linear solution. Factorization addresses non-uniform variance across dimensions, ensuring effective feature transformation. Experiments on LibriSpeech and FLEURS datasets show MKL-VC significantly improves content preservati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09709","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/2506.09709/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":"2506.09709","created_at":"2026-07-05T11:19:55.659664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.09709v1","created_at":"2026-07-05T11:19:55.659664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09709","created_at":"2026-07-05T11:19:55.659664+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z633BMNEQOU2","created_at":"2026-07-05T11:19:55.659664+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z633BMNEQOU2I5ZK","created_at":"2026-07-05T11:19:55.659664+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z633BMNE","created_at":"2026-07-05T11:19:55.659664+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.09709","citing_title":"Training-Free Voice Conversion with Factorized Optimal Transport","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z633BMNEQOU2I5ZKCWFTI2UKMA","json":"https://pith.science/pith/Z633BMNEQOU2I5ZKCWFTI2UKMA.json","graph_json":"https://pith.science/api/pith-number/Z633BMNEQOU2I5ZKCWFTI2UKMA/graph.json","events_json":"https://pith.science/api/pith-number/Z633BMNEQOU2I5ZKCWFTI2UKMA/events.json","paper":"https://pith.science/paper/Z633BMNE"},"agent_actions":{"view_html":"https://pith.science/pith/Z633BMNEQOU2I5ZKCWFTI2UKMA","download_json":"https://pith.science/pith/Z633BMNEQOU2I5ZKCWFTI2UKMA.json","view_paper":"https://pith.science/paper/Z633BMNE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.09709&json=true","fetch_graph":"https://pith.science/api/pith-number/Z633BMNEQOU2I5ZKCWFTI2UKMA/graph.json","fetch_events":"https://pith.science/api/pith-number/Z633BMNEQOU2I5ZKCWFTI2UKMA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z633BMNEQOU2I5ZKCWFTI2UKMA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z633BMNEQOU2I5ZKCWFTI2UKMA/action/storage_attestation","attest_author":"https://pith.science/pith/Z633BMNEQOU2I5ZKCWFTI2UKMA/action/author_attestation","sign_citation":"https://pith.science/pith/Z633BMNEQOU2I5ZKCWFTI2UKMA/action/citation_signature","submit_replication":"https://pith.science/pith/Z633BMNEQOU2I5ZKCWFTI2UKMA/action/replication_record"}},"created_at":"2026-07-05T11:19:55.659664+00:00","updated_at":"2026-07-05T11:19:55.659664+00:00"}