{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:DB77RA3KKOEJO7DM4TPXHVSDN7","short_pith_number":"pith:DB77RA3K","canonical_record":{"source":{"id":"2106.08352","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-15T18:03:48Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"44a0810f5e70ff67f8894f55d1b8364dfae24266ac5b7d3e107bfed2ff45b9ef","abstract_canon_sha256":"1becf243ad29f85b27e668be563a310b2cf3b869f462753484f223c1a06f6fc2"},"schema_version":"1.0"},"canonical_sha256":"187ff8836a5388977c6ce4df73d6436fe24216a733ffebd757113fc90fdfe5b4","source":{"kind":"arxiv","id":"2106.08352","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.08352","created_at":"2026-07-05T02:49:56Z"},{"alias_kind":"arxiv_version","alias_value":"2106.08352v1","created_at":"2026-07-05T02:49:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.08352","created_at":"2026-07-05T02:49:56Z"},{"alias_kind":"pith_short_12","alias_value":"DB77RA3KKOEJ","created_at":"2026-07-05T02:49:56Z"},{"alias_kind":"pith_short_16","alias_value":"DB77RA3KKOEJO7DM","created_at":"2026-07-05T02:49:56Z"},{"alias_kind":"pith_short_8","alias_value":"DB77RA3K","created_at":"2026-07-05T02:49:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:DB77RA3KKOEJO7DM4TPXHVSDN7","target":"record","payload":{"canonical_record":{"source":{"id":"2106.08352","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-15T18:03:48Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"44a0810f5e70ff67f8894f55d1b8364dfae24266ac5b7d3e107bfed2ff45b9ef","abstract_canon_sha256":"1becf243ad29f85b27e668be563a310b2cf3b869f462753484f223c1a06f6fc2"},"schema_version":"1.0"},"canonical_sha256":"187ff8836a5388977c6ce4df73d6436fe24216a733ffebd757113fc90fdfe5b4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:56.952762Z","signature_b64":"ogSCxXRmX3q2fXiveGpCLcFZs2nrnEBdER7JewadYAo8rfAu8zbFIgsIDujiJkEcVFt4KgiFveWyuycM3HUhBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"187ff8836a5388977c6ce4df73d6436fe24216a733ffebd757113fc90fdfe5b4","last_reissued_at":"2026-07-05T02:49:56.952266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:56.952266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.08352","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":"2026-07-05T02:49:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G1AWRkwrj2LcgkHHhAafKFi95tUnAR/sAmqiKaiUR0W0x+JJnfXM/Gk9uLiOr63TU/yvLkIXToLN628ghF4CBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:21:57.658671Z"},"content_sha256":"eb24a319d30f742980d2f546edfbf5707c2c30e6c3eadd003513da792985d88c","schema_version":"1.0","event_id":"sha256:eb24a319d30f742980d2f546edfbf5707c2c30e6c3eadd003513da792985d88c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:DB77RA3KKOEJO7DM4TPXHVSDN7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ctrl-P: Temporal Control of Prosodic Variation for Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Alexandra Torresquintero, Christopher G. R. Wallis, Devang S Ram Mohan, Jiameng Gao, Lorenzo Foglianti, Marlene Staib, Simon King, Tian Huey Teh, Vivian Hu","submitted_at":"2021-06-15T18:03:48Z","abstract_excerpt":"Text does not fully specify the spoken form, so text-to-speech models must be able to learn from speech data that vary in ways not explained by the corresponding text. One way to reduce the amount of unexplained variation in training data is to provide acoustic information as an additional learning signal. When generating speech, modifying this acoustic information enables multiple distinct renditions of a text to be produced.\n  Since much of the unexplained variation is in the prosody, we propose a model that generates speech explicitly conditioned on the three primary acoustic correlates of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.08352","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/2106.08352/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":"2026-07-05T02:49:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+SfDDMZ+EBPdQ7zSKsiTKFGoEr5yC4Qeylww6CWwy36vR3f5sQLPjpmGWWs4bJHjjWBoF2qRtmt2vbc/hZ++Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:21:57.659049Z"},"content_sha256":"f874e64f78573ce4c615dd6b637ea2f8a9b854d9d82411cb3f3ca8394be5922e","schema_version":"1.0","event_id":"sha256:f874e64f78573ce4c615dd6b637ea2f8a9b854d9d82411cb3f3ca8394be5922e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DB77RA3KKOEJO7DM4TPXHVSDN7/bundle.json","state_url":"https://pith.science/pith/DB77RA3KKOEJO7DM4TPXHVSDN7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DB77RA3KKOEJO7DM4TPXHVSDN7/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":"2026-07-06T19:21:57Z","links":{"resolver":"https://pith.science/pith/DB77RA3KKOEJO7DM4TPXHVSDN7","bundle":"https://pith.science/pith/DB77RA3KKOEJO7DM4TPXHVSDN7/bundle.json","state":"https://pith.science/pith/DB77RA3KKOEJO7DM4TPXHVSDN7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DB77RA3KKOEJO7DM4TPXHVSDN7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DB77RA3KKOEJO7DM4TPXHVSDN7","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":"1becf243ad29f85b27e668be563a310b2cf3b869f462753484f223c1a06f6fc2","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-15T18:03:48Z","title_canon_sha256":"44a0810f5e70ff67f8894f55d1b8364dfae24266ac5b7d3e107bfed2ff45b9ef"},"schema_version":"1.0","source":{"id":"2106.08352","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.08352","created_at":"2026-07-05T02:49:56Z"},{"alias_kind":"arxiv_version","alias_value":"2106.08352v1","created_at":"2026-07-05T02:49:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.08352","created_at":"2026-07-05T02:49:56Z"},{"alias_kind":"pith_short_12","alias_value":"DB77RA3KKOEJ","created_at":"2026-07-05T02:49:56Z"},{"alias_kind":"pith_short_16","alias_value":"DB77RA3KKOEJO7DM","created_at":"2026-07-05T02:49:56Z"},{"alias_kind":"pith_short_8","alias_value":"DB77RA3K","created_at":"2026-07-05T02:49:56Z"}],"graph_snapshots":[{"event_id":"sha256:f874e64f78573ce4c615dd6b637ea2f8a9b854d9d82411cb3f3ca8394be5922e","target":"graph","created_at":"2026-07-05T02:49:56Z","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/2106.08352/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text does not fully specify the spoken form, so text-to-speech models must be able to learn from speech data that vary in ways not explained by the corresponding text. One way to reduce the amount of unexplained variation in training data is to provide acoustic information as an additional learning signal. When generating speech, modifying this acoustic information enables multiple distinct renditions of a text to be produced.\n  Since much of the unexplained variation is in the prosody, we propose a model that generates speech explicitly conditioned on the three primary acoustic correlates of ","authors_text":"Alexandra Torresquintero, Christopher G. R. Wallis, Devang S Ram Mohan, Jiameng Gao, Lorenzo Foglianti, Marlene Staib, Simon King, Tian Huey Teh, Vivian Hu","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-15T18:03:48Z","title":"Ctrl-P: Temporal Control of Prosodic Variation for Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.08352","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:eb24a319d30f742980d2f546edfbf5707c2c30e6c3eadd003513da792985d88c","target":"record","created_at":"2026-07-05T02:49:56Z","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":"1becf243ad29f85b27e668be563a310b2cf3b869f462753484f223c1a06f6fc2","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-15T18:03:48Z","title_canon_sha256":"44a0810f5e70ff67f8894f55d1b8364dfae24266ac5b7d3e107bfed2ff45b9ef"},"schema_version":"1.0","source":{"id":"2106.08352","kind":"arxiv","version":1}},"canonical_sha256":"187ff8836a5388977c6ce4df73d6436fe24216a733ffebd757113fc90fdfe5b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"187ff8836a5388977c6ce4df73d6436fe24216a733ffebd757113fc90fdfe5b4","first_computed_at":"2026-07-05T02:49:56.952266Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:49:56.952266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ogSCxXRmX3q2fXiveGpCLcFZs2nrnEBdER7JewadYAo8rfAu8zbFIgsIDujiJkEcVFt4KgiFveWyuycM3HUhBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:49:56.952762Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.08352","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb24a319d30f742980d2f546edfbf5707c2c30e6c3eadd003513da792985d88c","sha256:f874e64f78573ce4c615dd6b637ea2f8a9b854d9d82411cb3f3ca8394be5922e"],"state_sha256":"e7ae5309f2ac82611ecbf40906b447376ef9c7ef5f8d2cf6059cec5a4ad5a0e6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Pg76mbM5uHT/kgxCr3K/vOQqg/zPew3LatC+B/Nzn+KgB0PzQ74CIn75KF9QuslDeAqEY9hz/khInzRmkrdAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:21:57.661281Z","bundle_sha256":"ae2a395afca4f73f699f6c9ce418349ae74d48ec9e123e4e3c7fb1a05863c3a8"}}