{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4CMNA52EMWEIZVS4XBH74ZBZR5","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":"6271f205752ad26405e0568cb31a56eaf1211c53a90269537846cbf145c1ecb4","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-11-04T12:20:21Z","title_canon_sha256":"a38aed14764c6318bd308d5dd35334111e417c336a5f002f820cfeda20e5aad8"},"schema_version":"1.0","source":{"id":"2011.02252","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.02252","created_at":"2026-07-05T01:49:10Z"},{"alias_kind":"arxiv_version","alias_value":"2011.02252v1","created_at":"2026-07-05T01:49:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.02252","created_at":"2026-07-05T01:49:10Z"},{"alias_kind":"pith_short_12","alias_value":"4CMNA52EMWEI","created_at":"2026-07-05T01:49:10Z"},{"alias_kind":"pith_short_16","alias_value":"4CMNA52EMWEIZVS4","created_at":"2026-07-05T01:49:10Z"},{"alias_kind":"pith_short_8","alias_value":"4CMNA52E","created_at":"2026-07-05T01:49:10Z"}],"graph_snapshots":[{"event_id":"sha256:6bb95ad0253d8dbe6aa5b5bd0276676a45ef62f2233355d6182d450b1178922e","target":"graph","created_at":"2026-07-05T01:49:10Z","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/2011.02252/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce Kathaka, a model trained with a novel two-stage training process for neural speech synthesis with contextually appropriate prosody. In Stage I, we learn a prosodic distribution at the sentence level from mel-spectrograms available during training. In Stage II, we propose a novel method to sample from this learnt prosodic distribution using the contextual information available in text. To do this, we use BERT on text, and graph-attention networks on parse trees extracted from text. We show a statistically significant relative improvement of $13.2\\%$ in naturalness ov","authors_text":"Alexis Moinet, Ammar Abbas, Arnaud Joly, Penny Karanasou, Sri Karlapati, Thomas Drugman, Zack Hodari","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-11-04T12:20:21Z","title":"Prosodic Representation Learning and Contextual Sampling for Neural Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.02252","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":"sha256:6bacf8e1772cd87e449b796761b8a6f83252a16a0fd57aadce657dbaf5dc520c","target":"record","created_at":"2026-07-05T01:49:10Z","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":"6271f205752ad26405e0568cb31a56eaf1211c53a90269537846cbf145c1ecb4","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-11-04T12:20:21Z","title_canon_sha256":"a38aed14764c6318bd308d5dd35334111e417c336a5f002f820cfeda20e5aad8"},"schema_version":"1.0","source":{"id":"2011.02252","kind":"arxiv","version":1}},"canonical_sha256":"e098d0774465888cd65cb84ffe64398f7e6beed11fb77ea7aba3e3f4b2b843af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e098d0774465888cd65cb84ffe64398f7e6beed11fb77ea7aba3e3f4b2b843af","first_computed_at":"2026-07-05T01:49:10.916404Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:49:10.916404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xmg/D+Wu01BI8DUTmcrk4vmViO/DkkSL2kwhCxwjQ178l9o+hcmInDTOV05WFaioCbF/l+CyDSAX5xoQSKhjBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:49:10.916800Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.02252","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bacf8e1772cd87e449b796761b8a6f83252a16a0fd57aadce657dbaf5dc520c","sha256:6bb95ad0253d8dbe6aa5b5bd0276676a45ef62f2233355d6182d450b1178922e"],"state_sha256":"cb8b1288a23ccce62f97ab92d6d9564fc336427cacccccb7deb0571d96a03a10"}