{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6666RP62OLW2RE7S3XBFPB36KX","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":"585baf0ce334f8872a95f63333657b319d4c24f00af6d011fe294ee48d6d49b2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-09-01T11:36:37Z","title_canon_sha256":"e9d9852c7d25c1d8da0230ee3d33e0eb8d892f7b1907a7d9e064e784fb9b1255"},"schema_version":"1.0","source":{"id":"2509.01391","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.01391","created_at":"2026-07-05T12:02:59Z"},{"alias_kind":"arxiv_version","alias_value":"2509.01391v1","created_at":"2026-07-05T12:02:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01391","created_at":"2026-07-05T12:02:59Z"},{"alias_kind":"pith_short_12","alias_value":"6666RP62OLW2","created_at":"2026-07-05T12:02:59Z"},{"alias_kind":"pith_short_16","alias_value":"6666RP62OLW2RE7S","created_at":"2026-07-05T12:02:59Z"},{"alias_kind":"pith_short_8","alias_value":"6666RP62","created_at":"2026-07-05T12:02:59Z"}],"graph_snapshots":[{"event_id":"sha256:b96e93a967f1b0733dd89e7406789c6c0c096e5270930ec516183148fdf57ac0","target":"graph","created_at":"2026-07-05T12:02:59Z","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/2509.01391/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study presents a novel approach to voice synthesis that can substitute the traditional grapheme-to-phoneme (G2P) conversion by using a deep learning-based model that generates discrete tokens directly from speech. Utilizing a pre-trained voice SSL model, we train a T5 encoder to produce pseudo-language labels from mixed-script texts (e.g., containing Kanji and Kana). This method eliminates the need for manual phonetic transcription, reducing costs and enhancing scalability, especially for large non-transcribed audio datasets. Our model matches the performance of conventional G2P-based tex","authors_text":"Daisuke Saito, Joonyong Park, Nobuaki Minematsu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-09-01T11:36:37Z","title":"MixedG2P-T5: G2P-free Speech Synthesis for Mixed-script texts using Speech Self-Supervised Learning and Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01391","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:d9d62eb1e10e16b432d8e076c021d4e9a4161f74f78ee1ec65e4eb173e236b42","target":"record","created_at":"2026-07-05T12:02:59Z","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":"585baf0ce334f8872a95f63333657b319d4c24f00af6d011fe294ee48d6d49b2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-09-01T11:36:37Z","title_canon_sha256":"e9d9852c7d25c1d8da0230ee3d33e0eb8d892f7b1907a7d9e064e784fb9b1255"},"schema_version":"1.0","source":{"id":"2509.01391","kind":"arxiv","version":1}},"canonical_sha256":"f7bde8bfda72eda893f2ddc257877e55df406279b7ba74028b4467568f870113","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7bde8bfda72eda893f2ddc257877e55df406279b7ba74028b4467568f870113","first_computed_at":"2026-07-05T12:02:59.717830Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:59.717830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kG2V9FyhIN5kOjmjRgTs/vIg11CTQ/x8o+Bzld4yAsGmqC2MaGhZLoKntmJ8gnY7mpJTbugvNXxCVLTmoa7mBg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:59.718323Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.01391","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9d62eb1e10e16b432d8e076c021d4e9a4161f74f78ee1ec65e4eb173e236b42","sha256:b96e93a967f1b0733dd89e7406789c6c0c096e5270930ec516183148fdf57ac0"],"state_sha256":"a8360352039896e668e08ecf47cd4f6af5414a6e8725646265ef24dc3c7f2bac"}