{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5546DJN6N4F3JEKZ3FPHFE6327","short_pith_number":"pith:5546DJN6","canonical_record":{"source":{"id":"2309.03364","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-06T21:16:58Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"0e8091be23202a242a8f84b6e33dc0eabc18cc1c11f6d9402e1fc5c1a68fd5e0","abstract_canon_sha256":"2194a23987edd577b66d8d8f18e8fc9e1b7e783eaae1a5681b7e75d39c998526"},"schema_version":"1.0"},"canonical_sha256":"ef79e1a5be6f0bb49159d95e7293dbd7e2f50a37369b59d445d31b61ba8be199","source":{"kind":"arxiv","id":"2309.03364","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.03364","created_at":"2026-07-05T06:48:27Z"},{"alias_kind":"arxiv_version","alias_value":"2309.03364v1","created_at":"2026-07-05T06:48:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.03364","created_at":"2026-07-05T06:48:27Z"},{"alias_kind":"pith_short_12","alias_value":"5546DJN6N4F3","created_at":"2026-07-05T06:48:27Z"},{"alias_kind":"pith_short_16","alias_value":"5546DJN6N4F3JEKZ","created_at":"2026-07-05T06:48:27Z"},{"alias_kind":"pith_short_8","alias_value":"5546DJN6","created_at":"2026-07-05T06:48:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5546DJN6N4F3JEKZ3FPHFE6327","target":"record","payload":{"canonical_record":{"source":{"id":"2309.03364","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-06T21:16:58Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"0e8091be23202a242a8f84b6e33dc0eabc18cc1c11f6d9402e1fc5c1a68fd5e0","abstract_canon_sha256":"2194a23987edd577b66d8d8f18e8fc9e1b7e783eaae1a5681b7e75d39c998526"},"schema_version":"1.0"},"canonical_sha256":"ef79e1a5be6f0bb49159d95e7293dbd7e2f50a37369b59d445d31b61ba8be199","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:27.020920Z","signature_b64":"3s7m7jcG3cTw2cprXs3zafGSVkrPQw0rRrEyQ0xcUwvef+szJoXYMKvTppzJRVhhD7jf5aUOGsxs2P92cbPGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef79e1a5be6f0bb49159d95e7293dbd7e2f50a37369b59d445d31b61ba8be199","last_reissued_at":"2026-07-05T06:48:27.020447Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:27.020447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.03364","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":"2026-07-05T06:48:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hEpOHN6J0ObQMLIuHuG78kIXvoa8HYUVnAwvgwRi2P4KE8nl+AZMdlqjG0rbFB1dNdP8W1I7wG0hP98fR1zdBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:43:08.009178Z"},"content_sha256":"f9163cc1a62c95c20d0697778e183c80bb47139d569b3c522ab57ddd5273208d","schema_version":"1.0","event_id":"sha256:f9163cc1a62c95c20d0697778e183c80bb47139d569b3c522ab57ddd5273208d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5546DJN6N4F3JEKZ3FPHFE6327","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Highly Controllable Diffusion-based Any-to-Any Voice Conversion Model with Frame-level Prosody Feature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Erik Visser, Kyungguen Byun, Sunkuk Moon","submitted_at":"2023-09-06T21:16:58Z","abstract_excerpt":"We propose a highly controllable voice manipulation system that can perform any-to-any voice conversion (VC) and prosody modulation simultaneously. State-of-the-art VC systems can transfer sentence-level characteristics such as speaker, emotion, and speaking style. However, manipulating the frame-level prosody, such as pitch, energy and speaking rate, still remains challenging. Our proposed model utilizes a frame-level prosody feature to effectively transfer such properties. Specifically, pitch and energy trajectories are integrated in a prosody conditioning module and then fed alongside speak"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.03364","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/2309.03364/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":"2026-07-05T06:48:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"veG4/3CKiAt5MiAkfkeP+KORvKIHzF+GlmSRD+MbsEnqpwmmM8/9/VPOcWylueXAojReTcZIEAoTPCkETtAQAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:43:08.009744Z"},"content_sha256":"04be6be9999dcf6a63c56d28afe2f700e2225412116a18705163f36388a513a1","schema_version":"1.0","event_id":"sha256:04be6be9999dcf6a63c56d28afe2f700e2225412116a18705163f36388a513a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5546DJN6N4F3JEKZ3FPHFE6327/bundle.json","state_url":"https://pith.science/pith/5546DJN6N4F3JEKZ3FPHFE6327/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5546DJN6N4F3JEKZ3FPHFE6327/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":"2026-08-06T16:43:08Z","links":{"resolver":"https://pith.science/pith/5546DJN6N4F3JEKZ3FPHFE6327","bundle":"https://pith.science/pith/5546DJN6N4F3JEKZ3FPHFE6327/bundle.json","state":"https://pith.science/pith/5546DJN6N4F3JEKZ3FPHFE6327/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5546DJN6N4F3JEKZ3FPHFE6327/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5546DJN6N4F3JEKZ3FPHFE6327","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":"2194a23987edd577b66d8d8f18e8fc9e1b7e783eaae1a5681b7e75d39c998526","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-06T21:16:58Z","title_canon_sha256":"0e8091be23202a242a8f84b6e33dc0eabc18cc1c11f6d9402e1fc5c1a68fd5e0"},"schema_version":"1.0","source":{"id":"2309.03364","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.03364","created_at":"2026-07-05T06:48:27Z"},{"alias_kind":"arxiv_version","alias_value":"2309.03364v1","created_at":"2026-07-05T06:48:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.03364","created_at":"2026-07-05T06:48:27Z"},{"alias_kind":"pith_short_12","alias_value":"5546DJN6N4F3","created_at":"2026-07-05T06:48:27Z"},{"alias_kind":"pith_short_16","alias_value":"5546DJN6N4F3JEKZ","created_at":"2026-07-05T06:48:27Z"},{"alias_kind":"pith_short_8","alias_value":"5546DJN6","created_at":"2026-07-05T06:48:27Z"}],"graph_snapshots":[{"event_id":"sha256:04be6be9999dcf6a63c56d28afe2f700e2225412116a18705163f36388a513a1","target":"graph","created_at":"2026-07-05T06:48:27Z","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/2309.03364/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a highly controllable voice manipulation system that can perform any-to-any voice conversion (VC) and prosody modulation simultaneously. State-of-the-art VC systems can transfer sentence-level characteristics such as speaker, emotion, and speaking style. However, manipulating the frame-level prosody, such as pitch, energy and speaking rate, still remains challenging. Our proposed model utilizes a frame-level prosody feature to effectively transfer such properties. Specifically, pitch and energy trajectories are integrated in a prosody conditioning module and then fed alongside speak","authors_text":"Erik Visser, Kyungguen Byun, Sunkuk Moon","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-06T21:16:58Z","title":"Highly Controllable Diffusion-based Any-to-Any Voice Conversion Model with Frame-level Prosody Feature"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.03364","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:f9163cc1a62c95c20d0697778e183c80bb47139d569b3c522ab57ddd5273208d","target":"record","created_at":"2026-07-05T06:48:27Z","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":"2194a23987edd577b66d8d8f18e8fc9e1b7e783eaae1a5681b7e75d39c998526","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-06T21:16:58Z","title_canon_sha256":"0e8091be23202a242a8f84b6e33dc0eabc18cc1c11f6d9402e1fc5c1a68fd5e0"},"schema_version":"1.0","source":{"id":"2309.03364","kind":"arxiv","version":1}},"canonical_sha256":"ef79e1a5be6f0bb49159d95e7293dbd7e2f50a37369b59d445d31b61ba8be199","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef79e1a5be6f0bb49159d95e7293dbd7e2f50a37369b59d445d31b61ba8be199","first_computed_at":"2026-07-05T06:48:27.020447Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:48:27.020447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3s7m7jcG3cTw2cprXs3zafGSVkrPQw0rRrEyQ0xcUwvef+szJoXYMKvTppzJRVhhD7jf5aUOGsxs2P92cbPGDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:48:27.020920Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.03364","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9163cc1a62c95c20d0697778e183c80bb47139d569b3c522ab57ddd5273208d","sha256:04be6be9999dcf6a63c56d28afe2f700e2225412116a18705163f36388a513a1"],"state_sha256":"aa3ad4cea1194af338de7e00e1190c2f3db1d257f790eba5edf9adc514133209"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7VqDxFROP6RZCOajctOj1QyBaohDWnBjfRH7C053k5S0zgxkcec62riStEX9JuksfirOq2dIB+c17VhG6B2BDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T16:43:08.014935Z","bundle_sha256":"711386da692173eb191592b86c81b3328b6c65586be85b52170cd5d936bd4654"}}