{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6666RP62OLW2RE7S3XBFPB36KX","short_pith_number":"pith:6666RP62","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"},"canonical_sha256":"f7bde8bfda72eda893f2ddc257877e55df406279b7ba74028b4467568f870113","source":{"kind":"arxiv","id":"2509.01391","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6666RP62OLW2RE7S3XBFPB36KX","target":"record","payload":{"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"},"canonical_sha256":"f7bde8bfda72eda893f2ddc257877e55df406279b7ba74028b4467568f870113","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"},"source_kind":"arxiv","source_id":"2509.01391","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:02:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3xo476KVcunKyn+XqHfxU/cFJwVi7pcHodXznEnsZ1ZNRObbtx4ixtUQiMXWDzqWX3HyXnBpMwXbsjODcCTTDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:42:49.283783Z"},"content_sha256":"d9d62eb1e10e16b432d8e076c021d4e9a4161f74f78ee1ec65e4eb173e236b42","schema_version":"1.0","event_id":"sha256:d9d62eb1e10e16b432d8e076c021d4e9a4161f74f78ee1ec65e4eb173e236b42"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6666RP62OLW2RE7S3XBFPB36KX","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:02:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hf21ovYaUlO4D6NS7QTsBhPyLggoWOJ7/TY9nPfAcx+TAfGYgP5lFIqnCtIN/vkRFGKnkSugWKRtvsnXPNVcCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:42:49.284372Z"},"content_sha256":"b96e93a967f1b0733dd89e7406789c6c0c096e5270930ec516183148fdf57ac0","schema_version":"1.0","event_id":"sha256:b96e93a967f1b0733dd89e7406789c6c0c096e5270930ec516183148fdf57ac0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6666RP62OLW2RE7S3XBFPB36KX/bundle.json","state_url":"https://pith.science/pith/6666RP62OLW2RE7S3XBFPB36KX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6666RP62OLW2RE7S3XBFPB36KX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T03:42:49Z","links":{"resolver":"https://pith.science/pith/6666RP62OLW2RE7S3XBFPB36KX","bundle":"https://pith.science/pith/6666RP62OLW2RE7S3XBFPB36KX/bundle.json","state":"https://pith.science/pith/6666RP62OLW2RE7S3XBFPB36KX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6666RP62OLW2RE7S3XBFPB36KX/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BZfw3BOIPOolcjZ2Ny1XZ5tE2qJ2UhsoFo3temgdVruj6XkGYmas64bkyLVfyE6WniW9p1Kwab0YF6/g/tu/Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:42:49.289481Z","bundle_sha256":"28c224de2516c48c6b63f7aac3bd66f87c385d7cee4d41d311b8300898c27680"}}