{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NOWLSFB3D5A2MWPVZ6TZ6FMFV6","short_pith_number":"pith:NOWLSFB3","schema_version":"1.0","canonical_sha256":"6bacb9143b1f41a659f5cfa79f1585af9ed1edf65ba80b6bac7a6e410706d01a","source":{"kind":"arxiv","id":"2411.02402","version":1},"attestation_state":"computed","paper":{"title":"Optimal Transport Maps are Good Voice Converters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alexander Korotin, Arip Asadulaev, Evgeny Burnaev, Rostislav Korst, Vahe Egiazarian, Vitalii Shutov, Yaroslav Grebnyak","submitted_at":"2024-10-17T22:48:53Z","abstract_excerpt":"Recently, neural network-based methods for computing optimal transport maps have been effectively applied to style transfer problems. However, the application of these methods to voice conversion is underexplored. In our paper, we fill this gap by investigating optimal transport as a framework for voice conversion. We present a variety of optimal transport algorithms designed for different data representations, such as mel-spectrograms and latent representation of self-supervised speech models. For the mel-spectogram data representation, we achieve strong results in terms of Frechet Audio Dist"},"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":"2411.02402","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-17T22:48:53Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"2b9f2c5786111f644e45cb0235adc24bc398accd618cef2997fb5e6665afd5b6","abstract_canon_sha256":"f7d795f71ff4e547b8ed8fa0235ae7f7f766046bcae3f9b9a58807696c49b59a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:11.261472Z","signature_b64":"tJgHH+kLvZqT9XWfmZyFETrBX5mfK0iAuUE9MxpSteViunoR6DKEkWpL1etp2l/EBxsBv6znGf3+ChXMBiclCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bacb9143b1f41a659f5cfa79f1585af9ed1edf65ba80b6bac7a6e410706d01a","last_reissued_at":"2026-07-05T09:31:11.260948Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:11.260948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Transport Maps are Good Voice Converters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alexander Korotin, Arip Asadulaev, Evgeny Burnaev, Rostislav Korst, Vahe Egiazarian, Vitalii Shutov, Yaroslav Grebnyak","submitted_at":"2024-10-17T22:48:53Z","abstract_excerpt":"Recently, neural network-based methods for computing optimal transport maps have been effectively applied to style transfer problems. However, the application of these methods to voice conversion is underexplored. In our paper, we fill this gap by investigating optimal transport as a framework for voice conversion. We present a variety of optimal transport algorithms designed for different data representations, such as mel-spectrograms and latent representation of self-supervised speech models. For the mel-spectogram data representation, we achieve strong results in terms of Frechet Audio Dist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02402","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/2411.02402/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":"2411.02402","created_at":"2026-07-05T09:31:11.261044+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.02402v1","created_at":"2026-07-05T09:31:11.261044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02402","created_at":"2026-07-05T09:31:11.261044+00:00"},{"alias_kind":"pith_short_12","alias_value":"NOWLSFB3D5A2","created_at":"2026-07-05T09:31:11.261044+00:00"},{"alias_kind":"pith_short_16","alias_value":"NOWLSFB3D5A2MWPV","created_at":"2026-07-05T09:31:11.261044+00:00"},{"alias_kind":"pith_short_8","alias_value":"NOWLSFB3","created_at":"2026-07-05T09:31:11.261044+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":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NOWLSFB3D5A2MWPVZ6TZ6FMFV6","json":"https://pith.science/pith/NOWLSFB3D5A2MWPVZ6TZ6FMFV6.json","graph_json":"https://pith.science/api/pith-number/NOWLSFB3D5A2MWPVZ6TZ6FMFV6/graph.json","events_json":"https://pith.science/api/pith-number/NOWLSFB3D5A2MWPVZ6TZ6FMFV6/events.json","paper":"https://pith.science/paper/NOWLSFB3"},"agent_actions":{"view_html":"https://pith.science/pith/NOWLSFB3D5A2MWPVZ6TZ6FMFV6","download_json":"https://pith.science/pith/NOWLSFB3D5A2MWPVZ6TZ6FMFV6.json","view_paper":"https://pith.science/paper/NOWLSFB3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.02402&json=true","fetch_graph":"https://pith.science/api/pith-number/NOWLSFB3D5A2MWPVZ6TZ6FMFV6/graph.json","fetch_events":"https://pith.science/api/pith-number/NOWLSFB3D5A2MWPVZ6TZ6FMFV6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NOWLSFB3D5A2MWPVZ6TZ6FMFV6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NOWLSFB3D5A2MWPVZ6TZ6FMFV6/action/storage_attestation","attest_author":"https://pith.science/pith/NOWLSFB3D5A2MWPVZ6TZ6FMFV6/action/author_attestation","sign_citation":"https://pith.science/pith/NOWLSFB3D5A2MWPVZ6TZ6FMFV6/action/citation_signature","submit_replication":"https://pith.science/pith/NOWLSFB3D5A2MWPVZ6TZ6FMFV6/action/replication_record"}},"created_at":"2026-07-05T09:31:11.261044+00:00","updated_at":"2026-07-05T09:31:11.261044+00:00"}