{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2TNAM7YS4PPPOMBOUXA7I5G5VM","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":"9b9cccd99cce19c362dcca09372574ac0986ef108e2fca02fa4480024a9bf0b4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-31T16:16:52Z","title_canon_sha256":"d0eec7cf7cfd0322ae90e69b7c3fab274f2fa484a598f28697dff9504fe51573"},"schema_version":"1.0","source":{"id":"2501.19258","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.19258","created_at":"2026-07-05T11:54:43Z"},{"alias_kind":"arxiv_version","alias_value":"2501.19258v2","created_at":"2026-07-05T11:54:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.19258","created_at":"2026-07-05T11:54:43Z"},{"alias_kind":"pith_short_12","alias_value":"2TNAM7YS4PPP","created_at":"2026-07-05T11:54:43Z"},{"alias_kind":"pith_short_16","alias_value":"2TNAM7YS4PPPOMBO","created_at":"2026-07-05T11:54:43Z"},{"alias_kind":"pith_short_8","alias_value":"2TNAM7YS","created_at":"2026-07-05T11:54:43Z"}],"graph_snapshots":[{"event_id":"sha256:afc4cf23511d2cf73dfad894ec9096885e95c6406ab060e9f097aee1b92079c5","target":"graph","created_at":"2026-07-05T11:54:43Z","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/2501.19258/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-Speech (TTS) synthesis faces the inherent challenge of producing multiple speech outputs with varying prosody given a single text input. While previous research has addressed this by predicting prosodic information from both text and speech, additional contextual information, such as video, remains under-utilized despite being available in many applications. This paper investigates the potential of integrating visual context to enhance prosody prediction. We propose a novel model, VisualSpeech, which incorporates visual and textual information for improving prosody generation in TTS. E","authors_text":"Anton Ragni, Shumin Que","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-31T16:16:52Z","title":"VisualSpeech: Enhancing Prosody Modeling in TTS Using Video"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.19258","kind":"arxiv","version":2},"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":"sha256:01502645442eff4ea042afbda157993d006cd4f6680fc608f99e8d6a7eb16cba","target":"record","created_at":"2026-07-05T11:54:43Z","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":"9b9cccd99cce19c362dcca09372574ac0986ef108e2fca02fa4480024a9bf0b4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-31T16:16:52Z","title_canon_sha256":"d0eec7cf7cfd0322ae90e69b7c3fab274f2fa484a598f28697dff9504fe51573"},"schema_version":"1.0","source":{"id":"2501.19258","kind":"arxiv","version":2}},"canonical_sha256":"d4da067f12e3def7302ea5c1f474ddab2b80e68e8241dac53474754d2361c633","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4da067f12e3def7302ea5c1f474ddab2b80e68e8241dac53474754d2361c633","first_computed_at":"2026-07-05T11:54:43.876940Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:54:43.876940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6xLp3r0hvZCzHp+fGIyPpbvB5+nWv2S9NgPNj4zqU3d8kgW/02RLGqT7Boo24Sq+OuU3+RyErTB6vuwhA4esBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:54:43.877346Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.19258","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01502645442eff4ea042afbda157993d006cd4f6680fc608f99e8d6a7eb16cba","sha256:afc4cf23511d2cf73dfad894ec9096885e95c6406ab060e9f097aee1b92079c5"],"state_sha256":"aaa673ba7ffca1e4c957564c8ad904b4157712b035c76ed53b2f860b0502bf72"}