{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6666RP62OLW2RE7S3XBFPB36KX","short_pith_number":"pith:6666RP62","schema_version":"1.0","canonical_sha256":"f7bde8bfda72eda893f2ddc257877e55df406279b7ba74028b4467568f870113","source":{"kind":"arxiv","id":"2509.01391","version":1},"attestation_state":"computed","paper":{"title":"MixedG2P-T5: G2P-free Speech Synthesis for Mixed-script texts using Speech Self-Supervised Learning and Language Model","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Daisuke Saito, Joonyong Park, Nobuaki Minematsu","submitted_at":"2025-09-01T11:36:37Z","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"},"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":"2509.01391","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-09-01T11:36:37Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e9d9852c7d25c1d8da0230ee3d33e0eb8d892f7b1907a7d9e064e784fb9b1255","abstract_canon_sha256":"585baf0ce334f8872a95f63333657b319d4c24f00af6d011fe294ee48d6d49b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:59.718323Z","signature_b64":"kG2V9FyhIN5kOjmjRgTs/vIg11CTQ/x8o+Bzld4yAsGmqC2MaGhZLoKntmJ8gnY7mpJTbugvNXxCVLTmoa7mBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7bde8bfda72eda893f2ddc257877e55df406279b7ba74028b4467568f870113","last_reissued_at":"2026-07-05T12:02:59.717830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:59.717830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MixedG2P-T5: G2P-free Speech Synthesis for Mixed-script texts using Speech Self-Supervised Learning and Language Model","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Daisuke Saito, Joonyong Park, Nobuaki Minematsu","submitted_at":"2025-09-01T11:36:37Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01391","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/2509.01391/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":"2509.01391","created_at":"2026-07-05T12:02:59.717889+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.01391v1","created_at":"2026-07-05T12:02:59.717889+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01391","created_at":"2026-07-05T12:02:59.717889+00:00"},{"alias_kind":"pith_short_12","alias_value":"6666RP62OLW2","created_at":"2026-07-05T12:02:59.717889+00:00"},{"alias_kind":"pith_short_16","alias_value":"6666RP62OLW2RE7S","created_at":"2026-07-05T12:02:59.717889+00:00"},{"alias_kind":"pith_short_8","alias_value":"6666RP62","created_at":"2026-07-05T12:02:59.717889+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/6666RP62OLW2RE7S3XBFPB36KX","json":"https://pith.science/pith/6666RP62OLW2RE7S3XBFPB36KX.json","graph_json":"https://pith.science/api/pith-number/6666RP62OLW2RE7S3XBFPB36KX/graph.json","events_json":"https://pith.science/api/pith-number/6666RP62OLW2RE7S3XBFPB36KX/events.json","paper":"https://pith.science/paper/6666RP62"},"agent_actions":{"view_html":"https://pith.science/pith/6666RP62OLW2RE7S3XBFPB36KX","download_json":"https://pith.science/pith/6666RP62OLW2RE7S3XBFPB36KX.json","view_paper":"https://pith.science/paper/6666RP62","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.01391&json=true","fetch_graph":"https://pith.science/api/pith-number/6666RP62OLW2RE7S3XBFPB36KX/graph.json","fetch_events":"https://pith.science/api/pith-number/6666RP62OLW2RE7S3XBFPB36KX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6666RP62OLW2RE7S3XBFPB36KX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6666RP62OLW2RE7S3XBFPB36KX/action/storage_attestation","attest_author":"https://pith.science/pith/6666RP62OLW2RE7S3XBFPB36KX/action/author_attestation","sign_citation":"https://pith.science/pith/6666RP62OLW2RE7S3XBFPB36KX/action/citation_signature","submit_replication":"https://pith.science/pith/6666RP62OLW2RE7S3XBFPB36KX/action/replication_record"}},"created_at":"2026-07-05T12:02:59.717889+00:00","updated_at":"2026-07-05T12:02:59.717889+00:00"}