{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:66TLYVESVDKNAUEEVTWHWLW7F3","short_pith_number":"pith:66TLYVES","schema_version":"1.0","canonical_sha256":"f7a6bc5492a8d4d05084acec7b2edf2eebfb2147eee3dc7897d9ce3766fee3eb","source":{"kind":"arxiv","id":"2206.07956","version":1},"attestation_state":"computed","paper":{"title":"Automatic Prosody Annotation with Pre-Trained Text-Speech Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Deng Cai, Dong Yu, Guangzhi Li, Jianwei Yu, Nuo Chen, Yan Wang, Yanyao Bian, Ziqian Dai","submitted_at":"2022-06-16T06:54:16Z","abstract_excerpt":"Prosodic boundary plays an important role in text-to-speech synthesis (TTS) in terms of naturalness and readability. However, the acquisition of prosodic boundary labels relies on manual annotation, which is costly and time-consuming. In this paper, we propose to automatically extract prosodic boundary labels from text-audio data via a neural text-speech model with pre-trained audio encoders. This model is pre-trained on text and speech data separately and jointly fine-tuned on TTS data in a triplet format: {speech, text, prosody}. The experimental results on both automatic evaluation and huma"},"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":"2206.07956","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-06-16T06:54:16Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"3adfbd60703012d58ea610453c941bc1121ba70b2945eda6278561c36d6ec73f","abstract_canon_sha256":"727b02c774bef947ee44fec90cceb94ec9d8ab9d477e34bb6f7968570ec91132"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:20.419486Z","signature_b64":"0TT3B4iabdTUa7HUkVYTc89MZWFTeh1Hru6AOxky2Yl8yvbNG5Ubn+TKwaP13a9bMSwToM8rMnZoJhn8pxPeCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7a6bc5492a8d4d05084acec7b2edf2eebfb2147eee3dc7897d9ce3766fee3eb","last_reissued_at":"2026-07-05T04:32:20.418928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:20.418928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Prosody Annotation with Pre-Trained Text-Speech Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Deng Cai, Dong Yu, Guangzhi Li, Jianwei Yu, Nuo Chen, Yan Wang, Yanyao Bian, Ziqian Dai","submitted_at":"2022-06-16T06:54:16Z","abstract_excerpt":"Prosodic boundary plays an important role in text-to-speech synthesis (TTS) in terms of naturalness and readability. However, the acquisition of prosodic boundary labels relies on manual annotation, which is costly and time-consuming. In this paper, we propose to automatically extract prosodic boundary labels from text-audio data via a neural text-speech model with pre-trained audio encoders. This model is pre-trained on text and speech data separately and jointly fine-tuned on TTS data in a triplet format: {speech, text, prosody}. The experimental results on both automatic evaluation and huma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07956","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/2206.07956/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":"2206.07956","created_at":"2026-07-05T04:32:20.418981+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.07956v1","created_at":"2026-07-05T04:32:20.418981+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07956","created_at":"2026-07-05T04:32:20.418981+00:00"},{"alias_kind":"pith_short_12","alias_value":"66TLYVESVDKN","created_at":"2026-07-05T04:32:20.418981+00:00"},{"alias_kind":"pith_short_16","alias_value":"66TLYVESVDKNAUEE","created_at":"2026-07-05T04:32:20.418981+00:00"},{"alias_kind":"pith_short_8","alias_value":"66TLYVES","created_at":"2026-07-05T04:32:20.418981+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/66TLYVESVDKNAUEEVTWHWLW7F3","json":"https://pith.science/pith/66TLYVESVDKNAUEEVTWHWLW7F3.json","graph_json":"https://pith.science/api/pith-number/66TLYVESVDKNAUEEVTWHWLW7F3/graph.json","events_json":"https://pith.science/api/pith-number/66TLYVESVDKNAUEEVTWHWLW7F3/events.json","paper":"https://pith.science/paper/66TLYVES"},"agent_actions":{"view_html":"https://pith.science/pith/66TLYVESVDKNAUEEVTWHWLW7F3","download_json":"https://pith.science/pith/66TLYVESVDKNAUEEVTWHWLW7F3.json","view_paper":"https://pith.science/paper/66TLYVES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.07956&json=true","fetch_graph":"https://pith.science/api/pith-number/66TLYVESVDKNAUEEVTWHWLW7F3/graph.json","fetch_events":"https://pith.science/api/pith-number/66TLYVESVDKNAUEEVTWHWLW7F3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/66TLYVESVDKNAUEEVTWHWLW7F3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/66TLYVESVDKNAUEEVTWHWLW7F3/action/storage_attestation","attest_author":"https://pith.science/pith/66TLYVESVDKNAUEEVTWHWLW7F3/action/author_attestation","sign_citation":"https://pith.science/pith/66TLYVESVDKNAUEEVTWHWLW7F3/action/citation_signature","submit_replication":"https://pith.science/pith/66TLYVESVDKNAUEEVTWHWLW7F3/action/replication_record"}},"created_at":"2026-07-05T04:32:20.418981+00:00","updated_at":"2026-07-05T04:32:20.418981+00:00"}