{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6AYPT3RXV5HSU5RDLYUSDQWQPL","short_pith_number":"pith:6AYPT3RX","schema_version":"1.0","canonical_sha256":"f030f9ee37af4f2a76235e2921c2d07ada6d258786c6ca8b141a4c7d71e19658","source":{"kind":"arxiv","id":"2509.00675","version":1},"attestation_state":"computed","paper":{"title":"Speaker-Conditioned Phrase Break Prediction for Text-to-Speech with Phoneme-Level Pre-trained Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Detai Xin, Dong Yang, Hiroshi Saruwatari, Takaaki Saeki, Tomoki Koriyama, Wataru Nakata, Yuki Saito","submitted_at":"2025-08-31T03:06:37Z","abstract_excerpt":"This paper advances phrase break prediction (also known as phrasing) in multi-speaker text-to-speech (TTS) systems. We integrate speaker-specific features by leveraging speaker embeddings to enhance the performance of the phrasing model. We further demonstrate that these speaker embeddings can capture speaker-related characteristics solely from the phrasing task. Besides, we explore the potential of pre-trained speaker embeddings for unseen speakers through a few-shot adaptation method. Furthermore, we pioneer the application of phoneme-level pre-trained language models to this TTS front-end t"},"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":"2509.00675","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-31T03:06:37Z","cross_cats_sorted":[],"title_canon_sha256":"a344c5a95295a1f6171d1d292e05cf5d9b4f9b02ff589a31af02e39b1f97dd76","abstract_canon_sha256":"709854e0445e070785d3591099585ceea0c92f45be46b20d54e2916f0aafe45f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:20.845488Z","signature_b64":"KaBthbSLB/9/Ku8UxcD3yuGIWI1VbXBXwIASpcPHiwsAgN4iQZDnB7L0tQOJT3bVnTEA3m+xPkm+59fgB81QAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f030f9ee37af4f2a76235e2921c2d07ada6d258786c6ca8b141a4c7d71e19658","last_reissued_at":"2026-07-05T12:02:20.845044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:20.845044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speaker-Conditioned Phrase Break Prediction for Text-to-Speech with Phoneme-Level Pre-trained Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Detai Xin, Dong Yang, Hiroshi Saruwatari, Takaaki Saeki, Tomoki Koriyama, Wataru Nakata, Yuki Saito","submitted_at":"2025-08-31T03:06:37Z","abstract_excerpt":"This paper advances phrase break prediction (also known as phrasing) in multi-speaker text-to-speech (TTS) systems. We integrate speaker-specific features by leveraging speaker embeddings to enhance the performance of the phrasing model. We further demonstrate that these speaker embeddings can capture speaker-related characteristics solely from the phrasing task. Besides, we explore the potential of pre-trained speaker embeddings for unseen speakers through a few-shot adaptation method. Furthermore, we pioneer the application of phoneme-level pre-trained language models to this TTS front-end t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00675","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/2509.00675/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":"2509.00675","created_at":"2026-07-05T12:02:20.845111+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.00675v1","created_at":"2026-07-05T12:02:20.845111+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00675","created_at":"2026-07-05T12:02:20.845111+00:00"},{"alias_kind":"pith_short_12","alias_value":"6AYPT3RXV5HS","created_at":"2026-07-05T12:02:20.845111+00:00"},{"alias_kind":"pith_short_16","alias_value":"6AYPT3RXV5HSU5RD","created_at":"2026-07-05T12:02:20.845111+00:00"},{"alias_kind":"pith_short_8","alias_value":"6AYPT3RX","created_at":"2026-07-05T12:02:20.845111+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/6AYPT3RXV5HSU5RDLYUSDQWQPL","json":"https://pith.science/pith/6AYPT3RXV5HSU5RDLYUSDQWQPL.json","graph_json":"https://pith.science/api/pith-number/6AYPT3RXV5HSU5RDLYUSDQWQPL/graph.json","events_json":"https://pith.science/api/pith-number/6AYPT3RXV5HSU5RDLYUSDQWQPL/events.json","paper":"https://pith.science/paper/6AYPT3RX"},"agent_actions":{"view_html":"https://pith.science/pith/6AYPT3RXV5HSU5RDLYUSDQWQPL","download_json":"https://pith.science/pith/6AYPT3RXV5HSU5RDLYUSDQWQPL.json","view_paper":"https://pith.science/paper/6AYPT3RX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.00675&json=true","fetch_graph":"https://pith.science/api/pith-number/6AYPT3RXV5HSU5RDLYUSDQWQPL/graph.json","fetch_events":"https://pith.science/api/pith-number/6AYPT3RXV5HSU5RDLYUSDQWQPL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6AYPT3RXV5HSU5RDLYUSDQWQPL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6AYPT3RXV5HSU5RDLYUSDQWQPL/action/storage_attestation","attest_author":"https://pith.science/pith/6AYPT3RXV5HSU5RDLYUSDQWQPL/action/author_attestation","sign_citation":"https://pith.science/pith/6AYPT3RXV5HSU5RDLYUSDQWQPL/action/citation_signature","submit_replication":"https://pith.science/pith/6AYPT3RXV5HSU5RDLYUSDQWQPL/action/replication_record"}},"created_at":"2026-07-05T12:02:20.845111+00:00","updated_at":"2026-07-05T12:02:20.845111+00:00"}