{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XRAUOU362R2VVLZJP35JKSWAXJ","short_pith_number":"pith:XRAUOU36","schema_version":"1.0","canonical_sha256":"bc4147537ed4755aaf297efa954ac0ba704e9e6c97188c90bfcd1021e5c56a29","source":{"kind":"arxiv","id":"2302.13652","version":1},"attestation_state":"computed","paper":{"title":"Duration-aware pause insertion using pre-trained language model for multi-speaker text-to-speech","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Detai Xin, Dong Yang, Hiroshi Saruwatari, Takaaki Saeki, Tomoki Koriyama, Yuki Saito","submitted_at":"2023-02-27T10:40:41Z","abstract_excerpt":"Pause insertion, also known as phrase break prediction and phrasing, is an essential part of TTS systems because proper pauses with natural duration significantly enhance the rhythm and intelligibility of synthetic speech. However, conventional phrasing models ignore various speakers' different styles of inserting silent pauses, which can degrade the performance of the model trained on a multi-speaker speech corpus. To this end, we propose more powerful pause insertion frameworks based on a pre-trained language model. Our approach uses bidirectional encoder representations from transformers (B"},"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":"2302.13652","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-02-27T10:40:41Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"66b3f7e6fca591ec22f638af5a2b5b04be4bd570c70bc87fc9e0bd9fb72e0439","abstract_canon_sha256":"e70f696ce1b5bb95f08339d4ea3fd6b1fd3d38cbb9b3c0c4177c3c44cc674cec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:49.600527Z","signature_b64":"N/lUyD+3kL4jS4E9FjO8S/xQbk0kTSAZuOEoN2la0OWEnylphq0cBLbRj0VCSg9ULrBJid9YvA/JVIkFFKQ5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc4147537ed4755aaf297efa954ac0ba704e9e6c97188c90bfcd1021e5c56a29","last_reissued_at":"2026-07-05T05:45:49.600067Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:49.600067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Duration-aware pause insertion using pre-trained language model for multi-speaker text-to-speech","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Detai Xin, Dong Yang, Hiroshi Saruwatari, Takaaki Saeki, Tomoki Koriyama, Yuki Saito","submitted_at":"2023-02-27T10:40:41Z","abstract_excerpt":"Pause insertion, also known as phrase break prediction and phrasing, is an essential part of TTS systems because proper pauses with natural duration significantly enhance the rhythm and intelligibility of synthetic speech. However, conventional phrasing models ignore various speakers' different styles of inserting silent pauses, which can degrade the performance of the model trained on a multi-speaker speech corpus. To this end, we propose more powerful pause insertion frameworks based on a pre-trained language model. Our approach uses bidirectional encoder representations from transformers (B"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.13652","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/2302.13652/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":"2302.13652","created_at":"2026-07-05T05:45:49.600122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.13652v1","created_at":"2026-07-05T05:45:49.600122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.13652","created_at":"2026-07-05T05:45:49.600122+00:00"},{"alias_kind":"pith_short_12","alias_value":"XRAUOU362R2V","created_at":"2026-07-05T05:45:49.600122+00:00"},{"alias_kind":"pith_short_16","alias_value":"XRAUOU362R2VVLZJ","created_at":"2026-07-05T05:45:49.600122+00:00"},{"alias_kind":"pith_short_8","alias_value":"XRAUOU36","created_at":"2026-07-05T05:45:49.600122+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/XRAUOU362R2VVLZJP35JKSWAXJ","json":"https://pith.science/pith/XRAUOU362R2VVLZJP35JKSWAXJ.json","graph_json":"https://pith.science/api/pith-number/XRAUOU362R2VVLZJP35JKSWAXJ/graph.json","events_json":"https://pith.science/api/pith-number/XRAUOU362R2VVLZJP35JKSWAXJ/events.json","paper":"https://pith.science/paper/XRAUOU36"},"agent_actions":{"view_html":"https://pith.science/pith/XRAUOU362R2VVLZJP35JKSWAXJ","download_json":"https://pith.science/pith/XRAUOU362R2VVLZJP35JKSWAXJ.json","view_paper":"https://pith.science/paper/XRAUOU36","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.13652&json=true","fetch_graph":"https://pith.science/api/pith-number/XRAUOU362R2VVLZJP35JKSWAXJ/graph.json","fetch_events":"https://pith.science/api/pith-number/XRAUOU362R2VVLZJP35JKSWAXJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XRAUOU362R2VVLZJP35JKSWAXJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XRAUOU362R2VVLZJP35JKSWAXJ/action/storage_attestation","attest_author":"https://pith.science/pith/XRAUOU362R2VVLZJP35JKSWAXJ/action/author_attestation","sign_citation":"https://pith.science/pith/XRAUOU362R2VVLZJP35JKSWAXJ/action/citation_signature","submit_replication":"https://pith.science/pith/XRAUOU362R2VVLZJP35JKSWAXJ/action/replication_record"}},"created_at":"2026-07-05T05:45:49.600122+00:00","updated_at":"2026-07-05T05:45:49.600122+00:00"}