{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CL6DXQ45RU5REJXSGM75RL45JS","short_pith_number":"pith:CL6DXQ45","schema_version":"1.0","canonical_sha256":"12fc3bc39d8d3b1226f2333fd8af9d4ca0f3f1a74ac3ee8f7cac24449d74edd4","source":{"kind":"arxiv","id":"2305.18975","version":1},"attestation_state":"computed","paper":{"title":"Voice Conversion With Just Nearest Neighbors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Benjamin van Niekerk, Herman Kamper, Matthew Baas","submitted_at":"2023-05-30T12:19:07Z","abstract_excerpt":"Any-to-any voice conversion aims to transform source speech into a target voice with just a few examples of the target speaker as a reference. Recent methods produce convincing conversions, but at the cost of increased complexity -- making results difficult to reproduce and build on. Instead, we keep it simple. We propose k-nearest neighbors voice conversion (kNN-VC): a straightforward yet effective method for any-to-any conversion. First, we extract self-supervised representations of the source and reference speech. To convert to the target speaker, we replace each frame of the source represe"},"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":"2305.18975","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-30T12:19:07Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"2a6fafb65cf6b258ac8a9943615277f4bf96563986c06c95482fa4f310741845","abstract_canon_sha256":"3506ea40cbc1a0638526b0f85bac4594bbfe9022396d526c66ff2e559800b0f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:35.519284Z","signature_b64":"xFQkAaDf3dr/FfkCKa80pLRWvrZeubEjOcuF2EAoiVDLkj023BOPSkJjL8gMgBhWKOLFLiobUpXBqM2nGXoiBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12fc3bc39d8d3b1226f2333fd8af9d4ca0f3f1a74ac3ee8f7cac24449d74edd4","last_reissued_at":"2026-07-05T06:15:35.518962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:35.518962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Voice Conversion With Just Nearest Neighbors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Benjamin van Niekerk, Herman Kamper, Matthew Baas","submitted_at":"2023-05-30T12:19:07Z","abstract_excerpt":"Any-to-any voice conversion aims to transform source speech into a target voice with just a few examples of the target speaker as a reference. Recent methods produce convincing conversions, but at the cost of increased complexity -- making results difficult to reproduce and build on. Instead, we keep it simple. We propose k-nearest neighbors voice conversion (kNN-VC): a straightforward yet effective method for any-to-any conversion. First, we extract self-supervised representations of the source and reference speech. To convert to the target speaker, we replace each frame of the source represe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18975","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/2305.18975/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":"2305.18975","created_at":"2026-07-05T06:15:35.519010+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18975v1","created_at":"2026-07-05T06:15:35.519010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18975","created_at":"2026-07-05T06:15:35.519010+00:00"},{"alias_kind":"pith_short_12","alias_value":"CL6DXQ45RU5R","created_at":"2026-07-05T06:15:35.519010+00:00"},{"alias_kind":"pith_short_16","alias_value":"CL6DXQ45RU5REJXS","created_at":"2026-07-05T06:15:35.519010+00:00"},{"alias_kind":"pith_short_8","alias_value":"CL6DXQ45","created_at":"2026-07-05T06:15:35.519010+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05678","citing_title":"Beyond Waveform Robustness: Robust Feature-Vocoder Adversarial Attacks on Automatic Speech Recognition","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CL6DXQ45RU5REJXSGM75RL45JS","json":"https://pith.science/pith/CL6DXQ45RU5REJXSGM75RL45JS.json","graph_json":"https://pith.science/api/pith-number/CL6DXQ45RU5REJXSGM75RL45JS/graph.json","events_json":"https://pith.science/api/pith-number/CL6DXQ45RU5REJXSGM75RL45JS/events.json","paper":"https://pith.science/paper/CL6DXQ45"},"agent_actions":{"view_html":"https://pith.science/pith/CL6DXQ45RU5REJXSGM75RL45JS","download_json":"https://pith.science/pith/CL6DXQ45RU5REJXSGM75RL45JS.json","view_paper":"https://pith.science/paper/CL6DXQ45","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18975&json=true","fetch_graph":"https://pith.science/api/pith-number/CL6DXQ45RU5REJXSGM75RL45JS/graph.json","fetch_events":"https://pith.science/api/pith-number/CL6DXQ45RU5REJXSGM75RL45JS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CL6DXQ45RU5REJXSGM75RL45JS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CL6DXQ45RU5REJXSGM75RL45JS/action/storage_attestation","attest_author":"https://pith.science/pith/CL6DXQ45RU5REJXSGM75RL45JS/action/author_attestation","sign_citation":"https://pith.science/pith/CL6DXQ45RU5REJXSGM75RL45JS/action/citation_signature","submit_replication":"https://pith.science/pith/CL6DXQ45RU5REJXSGM75RL45JS/action/replication_record"}},"created_at":"2026-07-05T06:15:35.519010+00:00","updated_at":"2026-07-05T06:15:35.519010+00:00"}