{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6AYPT3RXV5HSU5RDLYUSDQWQPL","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":"709854e0445e070785d3591099585ceea0c92f45be46b20d54e2916f0aafe45f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-31T03:06:37Z","title_canon_sha256":"a344c5a95295a1f6171d1d292e05cf5d9b4f9b02ff589a31af02e39b1f97dd76"},"schema_version":"1.0","source":{"id":"2509.00675","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00675","created_at":"2026-07-05T12:02:20Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00675v1","created_at":"2026-07-05T12:02:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00675","created_at":"2026-07-05T12:02:20Z"},{"alias_kind":"pith_short_12","alias_value":"6AYPT3RXV5HS","created_at":"2026-07-05T12:02:20Z"},{"alias_kind":"pith_short_16","alias_value":"6AYPT3RXV5HSU5RD","created_at":"2026-07-05T12:02:20Z"},{"alias_kind":"pith_short_8","alias_value":"6AYPT3RX","created_at":"2026-07-05T12:02:20Z"}],"graph_snapshots":[{"event_id":"sha256:293b48eea532c46ac59b21248a5bec0096e02256fd2e10b6ebce16a5a6807c3f","target":"graph","created_at":"2026-07-05T12:02:20Z","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/2509.00675/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Detai Xin, Dong Yang, Hiroshi Saruwatari, Takaaki Saeki, Tomoki Koriyama, Wataru Nakata, Yuki Saito","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-31T03:06:37Z","title":"Speaker-Conditioned Phrase Break Prediction for Text-to-Speech with Phoneme-Level Pre-trained Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00675","kind":"arxiv","version":1},"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:f9e37bbc85dd1175c77284c7b9713398b4924c9915497fe330119a56641e0c65","target":"record","created_at":"2026-07-05T12:02:20Z","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":"709854e0445e070785d3591099585ceea0c92f45be46b20d54e2916f0aafe45f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-31T03:06:37Z","title_canon_sha256":"a344c5a95295a1f6171d1d292e05cf5d9b4f9b02ff589a31af02e39b1f97dd76"},"schema_version":"1.0","source":{"id":"2509.00675","kind":"arxiv","version":1}},"canonical_sha256":"f030f9ee37af4f2a76235e2921c2d07ada6d258786c6ca8b141a4c7d71e19658","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f030f9ee37af4f2a76235e2921c2d07ada6d258786c6ca8b141a4c7d71e19658","first_computed_at":"2026-07-05T12:02:20.845044Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:20.845044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KaBthbSLB/9/Ku8UxcD3yuGIWI1VbXBXwIASpcPHiwsAgN4iQZDnB7L0tQOJT3bVnTEA3m+xPkm+59fgB81QAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:20.845488Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.00675","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9e37bbc85dd1175c77284c7b9713398b4924c9915497fe330119a56641e0c65","sha256:293b48eea532c46ac59b21248a5bec0096e02256fd2e10b6ebce16a5a6807c3f"],"state_sha256":"e24d193be671375bbdd21c204774b185e7034054b14059b2182f007c0da655f4"}