{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:GCUF2Q3ALFZKD3QIXI3ZCCDRAF","short_pith_number":"pith:GCUF2Q3A","canonical_record":{"source":{"id":"2203.16937","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-31T10:45:32Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"8108b24aa728425ff38133f78c31a6554027404520f2739325582afb3fff9682","abstract_canon_sha256":"0b432cc55c3b1c164d6ae703bd08659ee8226b1ad4f618127555a7d53080cf45"},"schema_version":"1.0"},"canonical_sha256":"30a85d43605972a1ee08ba37910871016f4e172b132c0096acdc4c91de27b8e5","source":{"kind":"arxiv","id":"2203.16937","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.16937","created_at":"2026-07-05T04:10:29Z"},{"alias_kind":"arxiv_version","alias_value":"2203.16937v1","created_at":"2026-07-05T04:10:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16937","created_at":"2026-07-05T04:10:29Z"},{"alias_kind":"pith_short_12","alias_value":"GCUF2Q3ALFZK","created_at":"2026-07-05T04:10:29Z"},{"alias_kind":"pith_short_16","alias_value":"GCUF2Q3ALFZKD3QI","created_at":"2026-07-05T04:10:29Z"},{"alias_kind":"pith_short_8","alias_value":"GCUF2Q3A","created_at":"2026-07-05T04:10:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:GCUF2Q3ALFZKD3QIXI3ZCCDRAF","target":"record","payload":{"canonical_record":{"source":{"id":"2203.16937","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-31T10:45:32Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"8108b24aa728425ff38133f78c31a6554027404520f2739325582afb3fff9682","abstract_canon_sha256":"0b432cc55c3b1c164d6ae703bd08659ee8226b1ad4f618127555a7d53080cf45"},"schema_version":"1.0"},"canonical_sha256":"30a85d43605972a1ee08ba37910871016f4e172b132c0096acdc4c91de27b8e5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:29.775084Z","signature_b64":"qH2o6RLWdpoCibe3ysQaehnUZFkVnjeATyKMypL7DWU/f1Y0o9aiPhN8sym3u/7JMAzk0vOjoVOAif5sWOdKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30a85d43605972a1ee08ba37910871016f4e172b132c0096acdc4c91de27b8e5","last_reissued_at":"2026-07-05T04:10:29.774734Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:29.774734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.16937","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:10:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XTJOrmc4sNKgKUSX/oRwGsiXnnCyFgMBc12n42+GGtjFL/CW1hFK2aOSR23s8dshOebnBefmEUqQyfWVwcYVBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:58:39.317247Z"},"content_sha256":"13386404f8e608ba3c07f627becd3bb077cfc554717e7af60f27e7ae10389a6d","schema_version":"1.0","event_id":"sha256:13386404f8e608ba3c07f627becd3bb077cfc554717e7af60f27e7ae10389a6d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:GCUF2Q3ALFZKD3QIXI3ZCCDRAF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HiFi-VC: High Quality ASR-Based Voice Conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"A. Kashkin, I. Karpukhin, S. Shishkin","submitted_at":"2022-03-31T10:45:32Z","abstract_excerpt":"The goal of voice conversion (VC) is to convert input voice to match the target speaker's voice while keeping text and prosody intact. VC is usually used in entertainment and speaking-aid systems, as well as applied for speech data generation and augmentation. The development of any-to-any VC systems, which are capable of generating voices unseen during model training, is of particular interest to both researchers and the industry. Despite recent progress, any-to-any conversion quality is still inferior to natural speech.\n  In this work, we propose a new any-to-any voice conversion pipeline. O"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16937","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/2203.16937/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:10:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P/zeeyouaOquFEDRpU4XCXOarQzxdepOafqCpPN+SzvM3idR45IceF96AYLYI6Fw/Ptbq4DGL9bHq6k+OxSBDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:58:39.318195Z"},"content_sha256":"22ad67d978f4ad5af1d7786fa1ec0aa09fbc3defd47c1fc54d0ce80f373585d1","schema_version":"1.0","event_id":"sha256:22ad67d978f4ad5af1d7786fa1ec0aa09fbc3defd47c1fc54d0ce80f373585d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GCUF2Q3ALFZKD3QIXI3ZCCDRAF/bundle.json","state_url":"https://pith.science/pith/GCUF2Q3ALFZKD3QIXI3ZCCDRAF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GCUF2Q3ALFZKD3QIXI3ZCCDRAF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T18:58:39Z","links":{"resolver":"https://pith.science/pith/GCUF2Q3ALFZKD3QIXI3ZCCDRAF","bundle":"https://pith.science/pith/GCUF2Q3ALFZKD3QIXI3ZCCDRAF/bundle.json","state":"https://pith.science/pith/GCUF2Q3ALFZKD3QIXI3ZCCDRAF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GCUF2Q3ALFZKD3QIXI3ZCCDRAF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GCUF2Q3ALFZKD3QIXI3ZCCDRAF","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":"0b432cc55c3b1c164d6ae703bd08659ee8226b1ad4f618127555a7d53080cf45","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-31T10:45:32Z","title_canon_sha256":"8108b24aa728425ff38133f78c31a6554027404520f2739325582afb3fff9682"},"schema_version":"1.0","source":{"id":"2203.16937","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.16937","created_at":"2026-07-05T04:10:29Z"},{"alias_kind":"arxiv_version","alias_value":"2203.16937v1","created_at":"2026-07-05T04:10:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16937","created_at":"2026-07-05T04:10:29Z"},{"alias_kind":"pith_short_12","alias_value":"GCUF2Q3ALFZK","created_at":"2026-07-05T04:10:29Z"},{"alias_kind":"pith_short_16","alias_value":"GCUF2Q3ALFZKD3QI","created_at":"2026-07-05T04:10:29Z"},{"alias_kind":"pith_short_8","alias_value":"GCUF2Q3A","created_at":"2026-07-05T04:10:29Z"}],"graph_snapshots":[{"event_id":"sha256:22ad67d978f4ad5af1d7786fa1ec0aa09fbc3defd47c1fc54d0ce80f373585d1","target":"graph","created_at":"2026-07-05T04:10:29Z","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/2203.16937/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of voice conversion (VC) is to convert input voice to match the target speaker's voice while keeping text and prosody intact. VC is usually used in entertainment and speaking-aid systems, as well as applied for speech data generation and augmentation. The development of any-to-any VC systems, which are capable of generating voices unseen during model training, is of particular interest to both researchers and the industry. Despite recent progress, any-to-any conversion quality is still inferior to natural speech.\n  In this work, we propose a new any-to-any voice conversion pipeline. O","authors_text":"A. Kashkin, I. Karpukhin, S. Shishkin","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-31T10:45:32Z","title":"HiFi-VC: High Quality ASR-Based Voice Conversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16937","kind":"arxiv","version":1},"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":"sha256:13386404f8e608ba3c07f627becd3bb077cfc554717e7af60f27e7ae10389a6d","target":"record","created_at":"2026-07-05T04:10:29Z","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":"0b432cc55c3b1c164d6ae703bd08659ee8226b1ad4f618127555a7d53080cf45","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-31T10:45:32Z","title_canon_sha256":"8108b24aa728425ff38133f78c31a6554027404520f2739325582afb3fff9682"},"schema_version":"1.0","source":{"id":"2203.16937","kind":"arxiv","version":1}},"canonical_sha256":"30a85d43605972a1ee08ba37910871016f4e172b132c0096acdc4c91de27b8e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30a85d43605972a1ee08ba37910871016f4e172b132c0096acdc4c91de27b8e5","first_computed_at":"2026-07-05T04:10:29.774734Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:10:29.774734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qH2o6RLWdpoCibe3ysQaehnUZFkVnjeATyKMypL7DWU/f1Y0o9aiPhN8sym3u/7JMAzk0vOjoVOAif5sWOdKBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:10:29.775084Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.16937","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13386404f8e608ba3c07f627becd3bb077cfc554717e7af60f27e7ae10389a6d","sha256:22ad67d978f4ad5af1d7786fa1ec0aa09fbc3defd47c1fc54d0ce80f373585d1"],"state_sha256":"6ee8155bd2ef80041615c66aa51d460625452603b74cb4f212f1f51d3561a3a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VH5J6uSfKS/BiHQQJ1iP0qqEEMO49YdawUBIebfDXTzhLvR9HNdr+jZa9NmIOn4J7OejbUwQjtvUX1qimiV2BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:58:39.327528Z","bundle_sha256":"8885d053bfa5ad01dfa4754be0d8d9252c8e675d3a1d3a5328c2fcb8b3b8756b"}}