{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TCLFXQARF44NFCKU4PCRHYGWUB","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":"1808e219fae837f3f06281453ea5c553a72bcecf18bd5599e6d68135d0a098ff","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T14:07:39Z","title_canon_sha256":"91e2080ea32975c87b5eec166b0ade0036960d513ff69670a4ad5b466f914780"},"schema_version":"1.0","source":{"id":"2412.11795","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11795","created_at":"2026-07-05T09:51:40Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11795v2","created_at":"2026-07-05T09:51:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11795","created_at":"2026-07-05T09:51:40Z"},{"alias_kind":"pith_short_12","alias_value":"TCLFXQARF44N","created_at":"2026-07-05T09:51:40Z"},{"alias_kind":"pith_short_16","alias_value":"TCLFXQARF44NFCKU","created_at":"2026-07-05T09:51:40Z"},{"alias_kind":"pith_short_8","alias_value":"TCLFXQAR","created_at":"2026-07-05T09:51:40Z"}],"graph_snapshots":[{"event_id":"sha256:1e59bfff3a682fbe404425133f2aa68e9bdb327f6294bf15f6bb6164125b32e0","target":"graph","created_at":"2026-07-05T09:51:40Z","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/2412.11795/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prosody contains rich information beyond the literal meaning of words, which is crucial for the intelligibility of speech. Current models still fall short in phrasing and intonation; they not only miss or misplace breaks when synthesizing long sentences with complex structures but also produce unnatural intonation. We propose ProsodyFM, a prosody-aware text-to-speech synthesis (TTS) model with a flow-matching (FM) backbone that aims to enhance the phrasing and intonation aspects of prosody. ProsodyFM introduces two key components: a Phrase Break Encoder to capture initial phrase break location","authors_text":"Bj\\\"orn W. Schuller, Junjie Chen, Xiangheng He, Zixing Zhang","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T14:07:39Z","title":"ProsodyFM: Unsupervised Phrasing and Intonation Control for Intelligible Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11795","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":"sha256:882cb6b0b4b03e3c9062afa62f09c541d8ef212d428b1449297d8a81e543c758","target":"record","created_at":"2026-07-05T09:51:40Z","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":"1808e219fae837f3f06281453ea5c553a72bcecf18bd5599e6d68135d0a098ff","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T14:07:39Z","title_canon_sha256":"91e2080ea32975c87b5eec166b0ade0036960d513ff69670a4ad5b466f914780"},"schema_version":"1.0","source":{"id":"2412.11795","kind":"arxiv","version":2}},"canonical_sha256":"98965bc0112f38d28954e3c513e0d6a07c08b756a8268c5e7d369e17c9040aa3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98965bc0112f38d28954e3c513e0d6a07c08b756a8268c5e7d369e17c9040aa3","first_computed_at":"2026-07-05T09:51:40.027977Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:40.027977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R/8/rum9Yz64HFGgILDJ+XASh9h9NZc+05tWIOhN0x9N+S5PbpebF46mhDonIRGdu+RUvAIzMcFbSxrJSqtECQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:40.028436Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11795","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:882cb6b0b4b03e3c9062afa62f09c541d8ef212d428b1449297d8a81e543c758","sha256:1e59bfff3a682fbe404425133f2aa68e9bdb327f6294bf15f6bb6164125b32e0"],"state_sha256":"535f697d679b7a511d225a51f03c1c6d3dc6ba51e97d8d47a079823f51262a09"}