{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:VZR3PALNOMHPKD436EB4Q5ESV4","short_pith_number":"pith:VZR3PALN","canonical_record":{"source":{"id":"2211.06535","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-12T00:54:09Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"2329b6f6f3af3d3c9a02e8ad0d7724d7f19fd9d04f8faf5fc7ba9da5589f83b8","abstract_canon_sha256":"af339533fe4fc212b024ef6f57916a619910553ea96778aadd631f3aa889e1f0"},"schema_version":"1.0"},"canonical_sha256":"ae63b7816d730ef50f9bf103c87492af012fbeac9f6c9337d8b7f0cae31d1934","source":{"kind":"arxiv","id":"2211.06535","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.06535","created_at":"2026-07-05T05:15:26Z"},{"alias_kind":"arxiv_version","alias_value":"2211.06535v1","created_at":"2026-07-05T05:15:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06535","created_at":"2026-07-05T05:15:26Z"},{"alias_kind":"pith_short_12","alias_value":"VZR3PALNOMHP","created_at":"2026-07-05T05:15:26Z"},{"alias_kind":"pith_short_16","alias_value":"VZR3PALNOMHPKD43","created_at":"2026-07-05T05:15:26Z"},{"alias_kind":"pith_short_8","alias_value":"VZR3PALN","created_at":"2026-07-05T05:15:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:VZR3PALNOMHPKD436EB4Q5ESV4","target":"record","payload":{"canonical_record":{"source":{"id":"2211.06535","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-12T00:54:09Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"2329b6f6f3af3d3c9a02e8ad0d7724d7f19fd9d04f8faf5fc7ba9da5589f83b8","abstract_canon_sha256":"af339533fe4fc212b024ef6f57916a619910553ea96778aadd631f3aa889e1f0"},"schema_version":"1.0"},"canonical_sha256":"ae63b7816d730ef50f9bf103c87492af012fbeac9f6c9337d8b7f0cae31d1934","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:26.101356Z","signature_b64":"PdTQcHOk/B4XCEfze2UgRpreEXW8yoUZHJUrc7KrzAUSCZwr0l2pzvWUFy9U9cQkzhXzV2zG4md7AtQB7N4PAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae63b7816d730ef50f9bf103c87492af012fbeac9f6c9337d8b7f0cae31d1934","last_reissued_at":"2026-07-05T05:15:26.100878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:26.100878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.06535","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":"2026-07-05T05:15:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jL3FpzytuaNsT//qBW0WrA+6MRvo5VbCuNvMNxFAhf077HVRPX+90pma4yoG5LL8vMmsksRcBCf2AO5I3+OECw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T10:54:18.509688Z"},"content_sha256":"497d61b0e6a7194db6bc052521e8cfcb92b4078cc1bd6a6a736f0b0c08124199","schema_version":"1.0","event_id":"sha256:497d61b0e6a7194db6bc052521e8cfcb92b4078cc1bd6a6a736f0b0c08124199"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:VZR3PALNOMHPKD436EB4Q5ESV4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A unified one-shot prosody and speaker conversion system with self-supervised discrete speech units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Alexander Rudnicky, Li-Wei Chen, Shinji Watanabe","submitted_at":"2022-11-12T00:54:09Z","abstract_excerpt":"We present a unified system to realize one-shot voice conversion (VC) on the pitch, rhythm, and speaker attributes. Existing works generally ignore the correlation between prosody and language content, leading to the degradation of naturalness in converted speech. Additionally, the lack of proper language features prevents these systems from accurately preserving language content after conversion. To address these issues, we devise a cascaded modular system leveraging self-supervised discrete speech units as language representation. These discrete units provide duration information essential f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.06535","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/2211.06535/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":"2026-07-05T05:15:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qwaYwIzl/lPnHd3M+eYx5+vZ9nKpMBTCPuyA2vdMIHsmyvzO69nPoBX3NaE3jsOPkji3zocNby7rYBm0vzf6CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T10:54:18.510206Z"},"content_sha256":"134a445eb5f8a2b37937307f40cdd505752333dccb7742f2b41e266f26bdb377","schema_version":"1.0","event_id":"sha256:134a445eb5f8a2b37937307f40cdd505752333dccb7742f2b41e266f26bdb377"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VZR3PALNOMHPKD436EB4Q5ESV4/bundle.json","state_url":"https://pith.science/pith/VZR3PALNOMHPKD436EB4Q5ESV4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VZR3PALNOMHPKD436EB4Q5ESV4/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":"2026-08-18T10:54:18Z","links":{"resolver":"https://pith.science/pith/VZR3PALNOMHPKD436EB4Q5ESV4","bundle":"https://pith.science/pith/VZR3PALNOMHPKD436EB4Q5ESV4/bundle.json","state":"https://pith.science/pith/VZR3PALNOMHPKD436EB4Q5ESV4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VZR3PALNOMHPKD436EB4Q5ESV4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VZR3PALNOMHPKD436EB4Q5ESV4","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":"af339533fe4fc212b024ef6f57916a619910553ea96778aadd631f3aa889e1f0","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-12T00:54:09Z","title_canon_sha256":"2329b6f6f3af3d3c9a02e8ad0d7724d7f19fd9d04f8faf5fc7ba9da5589f83b8"},"schema_version":"1.0","source":{"id":"2211.06535","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.06535","created_at":"2026-07-05T05:15:26Z"},{"alias_kind":"arxiv_version","alias_value":"2211.06535v1","created_at":"2026-07-05T05:15:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06535","created_at":"2026-07-05T05:15:26Z"},{"alias_kind":"pith_short_12","alias_value":"VZR3PALNOMHP","created_at":"2026-07-05T05:15:26Z"},{"alias_kind":"pith_short_16","alias_value":"VZR3PALNOMHPKD43","created_at":"2026-07-05T05:15:26Z"},{"alias_kind":"pith_short_8","alias_value":"VZR3PALN","created_at":"2026-07-05T05:15:26Z"}],"graph_snapshots":[{"event_id":"sha256:134a445eb5f8a2b37937307f40cdd505752333dccb7742f2b41e266f26bdb377","target":"graph","created_at":"2026-07-05T05:15:26Z","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/2211.06535/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a unified system to realize one-shot voice conversion (VC) on the pitch, rhythm, and speaker attributes. Existing works generally ignore the correlation between prosody and language content, leading to the degradation of naturalness in converted speech. Additionally, the lack of proper language features prevents these systems from accurately preserving language content after conversion. To address these issues, we devise a cascaded modular system leveraging self-supervised discrete speech units as language representation. These discrete units provide duration information essential f","authors_text":"Alexander Rudnicky, Li-Wei Chen, Shinji Watanabe","cross_cats":["cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-12T00:54:09Z","title":"A unified one-shot prosody and speaker conversion system with self-supervised discrete speech units"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.06535","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":"sha256:497d61b0e6a7194db6bc052521e8cfcb92b4078cc1bd6a6a736f0b0c08124199","target":"record","created_at":"2026-07-05T05:15:26Z","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":"af339533fe4fc212b024ef6f57916a619910553ea96778aadd631f3aa889e1f0","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-12T00:54:09Z","title_canon_sha256":"2329b6f6f3af3d3c9a02e8ad0d7724d7f19fd9d04f8faf5fc7ba9da5589f83b8"},"schema_version":"1.0","source":{"id":"2211.06535","kind":"arxiv","version":1}},"canonical_sha256":"ae63b7816d730ef50f9bf103c87492af012fbeac9f6c9337d8b7f0cae31d1934","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae63b7816d730ef50f9bf103c87492af012fbeac9f6c9337d8b7f0cae31d1934","first_computed_at":"2026-07-05T05:15:26.100878Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:15:26.100878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PdTQcHOk/B4XCEfze2UgRpreEXW8yoUZHJUrc7KrzAUSCZwr0l2pzvWUFy9U9cQkzhXzV2zG4md7AtQB7N4PAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:15:26.101356Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.06535","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:497d61b0e6a7194db6bc052521e8cfcb92b4078cc1bd6a6a736f0b0c08124199","sha256:134a445eb5f8a2b37937307f40cdd505752333dccb7742f2b41e266f26bdb377"],"state_sha256":"8560574f1d931687043ed2edf0ad48bd2d645a0e12d368afbc650568ebc61037"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N4lTH7lg1mr7f7PYoBSnlYXESpGJ9D9jTTX/NleWsxqsiRJEjksI1+Axg5/TiER9lIbOpYiRBKp/yBSSnISGAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T10:54:18.513815Z","bundle_sha256":"1a72fb064de5172fa5cbb3dd23c676e1be35ce5afeeaddf98702351c210561c4"}}