{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5J2HVSI3XVUXGTPTDAQJ37GUL3","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":"f43c7bc2b97d368328b5fd049e382efbb9311d8377def1bb84607600e7575039","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-04T13:02:27Z","title_canon_sha256":"fd79f59c590b1d9312cb7c1b4e76ce534bef019b13404de6d38683cd4165f7f4"},"schema_version":"1.0","source":{"id":"2309.01576","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.01576","created_at":"2026-07-05T06:47:39Z"},{"alias_kind":"arxiv_version","alias_value":"2309.01576v1","created_at":"2026-07-05T06:47:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01576","created_at":"2026-07-05T06:47:39Z"},{"alias_kind":"pith_short_12","alias_value":"5J2HVSI3XVUX","created_at":"2026-07-05T06:47:39Z"},{"alias_kind":"pith_short_16","alias_value":"5J2HVSI3XVUXGTPT","created_at":"2026-07-05T06:47:39Z"},{"alias_kind":"pith_short_8","alias_value":"5J2HVSI3","created_at":"2026-07-05T06:47:39Z"}],"graph_snapshots":[{"event_id":"sha256:0f3f28b81f1f0cd66295e9b9931b1f7ffb1b320e825b7b38e77a3a07373e05e5","target":"graph","created_at":"2026-07-05T06:47:39Z","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/2309.01576/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State-of-the-art text-to-speech (TTS) systems have utilized pretrained language models (PLMs) to enhance prosody and create more natural-sounding speech. However, while PLMs have been extensively researched for natural language understanding (NLU), their impact on TTS has been overlooked. In this study, we aim to address this gap by conducting a comparative analysis of different PLMs for two TTS tasks: prosody prediction and pause prediction. Firstly, we trained a prosody prediction model using 15 different PLMs. Our findings revealed a logarithmic relationship between model size and quality, ","authors_text":"Alexis Moinet, Bastian Schnell, Marcel Granero-Moya, Nicole Peinelt, Penny Karanasou, Sri Karlapati, Thomas Drugman","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-04T13:02:27Z","title":"A Comparative Analysis of Pretrained Language Models for Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01576","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:c513927f5407028530480e2ed0879ff887d0d9397a05e55a715db72e6483c740","target":"record","created_at":"2026-07-05T06:47:39Z","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":"f43c7bc2b97d368328b5fd049e382efbb9311d8377def1bb84607600e7575039","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-04T13:02:27Z","title_canon_sha256":"fd79f59c590b1d9312cb7c1b4e76ce534bef019b13404de6d38683cd4165f7f4"},"schema_version":"1.0","source":{"id":"2309.01576","kind":"arxiv","version":1}},"canonical_sha256":"ea747ac91bbd69734df318209dfcd45ecaec4b322de74d6a4e22ec49cc5b4c60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea747ac91bbd69734df318209dfcd45ecaec4b322de74d6a4e22ec49cc5b4c60","first_computed_at":"2026-07-05T06:47:39.937338Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:47:39.937338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t4Jn0PlSAfKQSF4IvOGeaQbjEtPIxOQd0L/Py+hRuka/g8/uXy4dgVj1SRVEj54901LBPbwBQbrpYoZxqLrWDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:47:39.937734Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.01576","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c513927f5407028530480e2ed0879ff887d0d9397a05e55a715db72e6483c740","sha256:0f3f28b81f1f0cd66295e9b9931b1f7ffb1b320e825b7b38e77a3a07373e05e5"],"state_sha256":"6e30281ea5f33ae9d08cc15c6a2d01fec3bce1f0050b3ad1f3f3ce217d790010"}