{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TCLFXQARF44NFCKU4PCRHYGWUB","short_pith_number":"pith:TCLFXQAR","schema_version":"1.0","canonical_sha256":"98965bc0112f38d28954e3c513e0d6a07c08b756a8268c5e7d369e17c9040aa3","source":{"kind":"arxiv","id":"2412.11795","version":2},"attestation_state":"computed","paper":{"title":"ProsodyFM: Unsupervised Phrasing and Intonation Control for Intelligible Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bj\\\"orn W. Schuller, Junjie Chen, Xiangheng He, Zixing Zhang","submitted_at":"2024-12-16T14:07:39Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.11795","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T14:07:39Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"91e2080ea32975c87b5eec166b0ade0036960d513ff69670a4ad5b466f914780","abstract_canon_sha256":"1808e219fae837f3f06281453ea5c553a72bcecf18bd5599e6d68135d0a098ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:40.028436Z","signature_b64":"R/8/rum9Yz64HFGgILDJ+XASh9h9NZc+05tWIOhN0x9N+S5PbpebF46mhDonIRGdu+RUvAIzMcFbSxrJSqtECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98965bc0112f38d28954e3c513e0d6a07c08b756a8268c5e7d369e17c9040aa3","last_reissued_at":"2026-07-05T09:51:40.027977Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:40.027977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProsodyFM: Unsupervised Phrasing and Intonation Control for Intelligible Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bj\\\"orn W. Schuller, Junjie Chen, Xiangheng He, Zixing Zhang","submitted_at":"2024-12-16T14:07:39Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11795","kind":"arxiv","version":2},"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/2412.11795/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.11795","created_at":"2026-07-05T09:51:40.028036+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11795v2","created_at":"2026-07-05T09:51:40.028036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11795","created_at":"2026-07-05T09:51:40.028036+00:00"},{"alias_kind":"pith_short_12","alias_value":"TCLFXQARF44N","created_at":"2026-07-05T09:51:40.028036+00:00"},{"alias_kind":"pith_short_16","alias_value":"TCLFXQARF44NFCKU","created_at":"2026-07-05T09:51:40.028036+00:00"},{"alias_kind":"pith_short_8","alias_value":"TCLFXQAR","created_at":"2026-07-05T09:51:40.028036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TCLFXQARF44NFCKU4PCRHYGWUB","json":"https://pith.science/pith/TCLFXQARF44NFCKU4PCRHYGWUB.json","graph_json":"https://pith.science/api/pith-number/TCLFXQARF44NFCKU4PCRHYGWUB/graph.json","events_json":"https://pith.science/api/pith-number/TCLFXQARF44NFCKU4PCRHYGWUB/events.json","paper":"https://pith.science/paper/TCLFXQAR"},"agent_actions":{"view_html":"https://pith.science/pith/TCLFXQARF44NFCKU4PCRHYGWUB","download_json":"https://pith.science/pith/TCLFXQARF44NFCKU4PCRHYGWUB.json","view_paper":"https://pith.science/paper/TCLFXQAR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11795&json=true","fetch_graph":"https://pith.science/api/pith-number/TCLFXQARF44NFCKU4PCRHYGWUB/graph.json","fetch_events":"https://pith.science/api/pith-number/TCLFXQARF44NFCKU4PCRHYGWUB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TCLFXQARF44NFCKU4PCRHYGWUB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TCLFXQARF44NFCKU4PCRHYGWUB/action/storage_attestation","attest_author":"https://pith.science/pith/TCLFXQARF44NFCKU4PCRHYGWUB/action/author_attestation","sign_citation":"https://pith.science/pith/TCLFXQARF44NFCKU4PCRHYGWUB/action/citation_signature","submit_replication":"https://pith.science/pith/TCLFXQARF44NFCKU4PCRHYGWUB/action/replication_record"}},"created_at":"2026-07-05T09:51:40.028036+00:00","updated_at":"2026-07-05T09:51:40.028036+00:00"}