{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MPDOYBH2MPGRDBY5A6VH5PDGCL","short_pith_number":"pith:MPDOYBH2","canonical_record":{"source":{"id":"2401.10465","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-19T03:37:27Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"d4a1d060c291915dd681e4c0869d521052eb7519ce2a7819095dc4c26d485265","abstract_canon_sha256":"c5d85bb13b31f377b3178b736d5fd8c2201cea68a3715527f0b67c4687f8cebe"},"schema_version":"1.0"},"canonical_sha256":"63c6ec04fa63cd11871d07aa7ebc6612ccee7956bb769608abb588445d0eaace","source":{"kind":"arxiv","id":"2401.10465","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.10465","created_at":"2026-07-05T07:35:26Z"},{"alias_kind":"arxiv_version","alias_value":"2401.10465v1","created_at":"2026-07-05T07:35:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10465","created_at":"2026-07-05T07:35:26Z"},{"alias_kind":"pith_short_12","alias_value":"MPDOYBH2MPGR","created_at":"2026-07-05T07:35:26Z"},{"alias_kind":"pith_short_16","alias_value":"MPDOYBH2MPGRDBY5","created_at":"2026-07-05T07:35:26Z"},{"alias_kind":"pith_short_8","alias_value":"MPDOYBH2","created_at":"2026-07-05T07:35:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MPDOYBH2MPGRDBY5A6VH5PDGCL","target":"record","payload":{"canonical_record":{"source":{"id":"2401.10465","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-19T03:37:27Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"d4a1d060c291915dd681e4c0869d521052eb7519ce2a7819095dc4c26d485265","abstract_canon_sha256":"c5d85bb13b31f377b3178b736d5fd8c2201cea68a3715527f0b67c4687f8cebe"},"schema_version":"1.0"},"canonical_sha256":"63c6ec04fa63cd11871d07aa7ebc6612ccee7956bb769608abb588445d0eaace","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:26.726707Z","signature_b64":"6RRnfP/JJ/GvmhFJSkhLZmKz/Zbt+wuXkfDcCQgFc0d9ZBcBLI9bjN8OC/Vo5bVxat3vzJgrTbX28LVw6+VAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63c6ec04fa63cd11871d07aa7ebc6612ccee7956bb769608abb588445d0eaace","last_reissued_at":"2026-07-05T07:35:26.726190Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:26.726190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.10465","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":"2026-07-05T07:35:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GMhsuPIzMO2XxQ+BIZHP8Hgq1vHczsFq5AOY2wZG1J0HmqON3ttFxI7r8rScRVWj6yDsipJ/2Jioluy3X0mBAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:48:47.873887Z"},"content_sha256":"88126529a9cbdb15ebbe098b05f47aae9f48515c4bdd8e1859fd264cfdcf9ff7","schema_version":"1.0","event_id":"sha256:88126529a9cbdb15ebbe098b05f47aae9f48515c4bdd8e1859fd264cfdcf9ff7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MPDOYBH2MPGRDBY5A6VH5PDGCL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data-driven grapheme-to-phoneme representations for a lexicon-free text-to-speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abhinav Garg, Chanwoo Kim, Dhananjaya Gowda, Jiyeon Kim, Sushil Khyalia","submitted_at":"2024-01-19T03:37:27Z","abstract_excerpt":"Grapheme-to-Phoneme (G2P) is an essential first step in any modern, high-quality Text-to-Speech (TTS) system. Most of the current G2P systems rely on carefully hand-crafted lexicons developed by experts. This poses a two-fold problem. Firstly, the lexicons are generated using a fixed phoneme set, usually, ARPABET or IPA, which might not be the most optimal way to represent phonemes for all languages. Secondly, the man-hours required to produce such an expert lexicon are very high. In this paper, we eliminate both of these issues by using recent advances in self-supervised learning to obtain da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10465","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/2401.10465/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":"2026-07-05T07:35:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0uf4xXDBXhyecQ3qdwLOF0LxY+KzOuzQTsrqfLPKZ56s4+5oKZ974TTihInyHbxlYXkfxij7IvWj+yVZhhLnAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:48:47.874819Z"},"content_sha256":"c526ad85188b6cccbaed1e24b1a772f2fcc593d038f566f3bc4e4c59d4189b3f","schema_version":"1.0","event_id":"sha256:c526ad85188b6cccbaed1e24b1a772f2fcc593d038f566f3bc4e4c59d4189b3f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MPDOYBH2MPGRDBY5A6VH5PDGCL/bundle.json","state_url":"https://pith.science/pith/MPDOYBH2MPGRDBY5A6VH5PDGCL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MPDOYBH2MPGRDBY5A6VH5PDGCL/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":"2026-08-04T11:48:47Z","links":{"resolver":"https://pith.science/pith/MPDOYBH2MPGRDBY5A6VH5PDGCL","bundle":"https://pith.science/pith/MPDOYBH2MPGRDBY5A6VH5PDGCL/bundle.json","state":"https://pith.science/pith/MPDOYBH2MPGRDBY5A6VH5PDGCL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MPDOYBH2MPGRDBY5A6VH5PDGCL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MPDOYBH2MPGRDBY5A6VH5PDGCL","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":"c5d85bb13b31f377b3178b736d5fd8c2201cea68a3715527f0b67c4687f8cebe","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-19T03:37:27Z","title_canon_sha256":"d4a1d060c291915dd681e4c0869d521052eb7519ce2a7819095dc4c26d485265"},"schema_version":"1.0","source":{"id":"2401.10465","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.10465","created_at":"2026-07-05T07:35:26Z"},{"alias_kind":"arxiv_version","alias_value":"2401.10465v1","created_at":"2026-07-05T07:35:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10465","created_at":"2026-07-05T07:35:26Z"},{"alias_kind":"pith_short_12","alias_value":"MPDOYBH2MPGR","created_at":"2026-07-05T07:35:26Z"},{"alias_kind":"pith_short_16","alias_value":"MPDOYBH2MPGRDBY5","created_at":"2026-07-05T07:35:26Z"},{"alias_kind":"pith_short_8","alias_value":"MPDOYBH2","created_at":"2026-07-05T07:35:26Z"}],"graph_snapshots":[{"event_id":"sha256:c526ad85188b6cccbaed1e24b1a772f2fcc593d038f566f3bc4e4c59d4189b3f","target":"graph","created_at":"2026-07-05T07:35:26Z","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/2401.10465/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Grapheme-to-Phoneme (G2P) is an essential first step in any modern, high-quality Text-to-Speech (TTS) system. Most of the current G2P systems rely on carefully hand-crafted lexicons developed by experts. This poses a two-fold problem. Firstly, the lexicons are generated using a fixed phoneme set, usually, ARPABET or IPA, which might not be the most optimal way to represent phonemes for all languages. Secondly, the man-hours required to produce such an expert lexicon are very high. In this paper, we eliminate both of these issues by using recent advances in self-supervised learning to obtain da","authors_text":"Abhinav Garg, Chanwoo Kim, Dhananjaya Gowda, Jiyeon Kim, Sushil Khyalia","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-19T03:37:27Z","title":"Data-driven grapheme-to-phoneme representations for a lexicon-free text-to-speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10465","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":"sha256:88126529a9cbdb15ebbe098b05f47aae9f48515c4bdd8e1859fd264cfdcf9ff7","target":"record","created_at":"2026-07-05T07:35:26Z","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":"c5d85bb13b31f377b3178b736d5fd8c2201cea68a3715527f0b67c4687f8cebe","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-19T03:37:27Z","title_canon_sha256":"d4a1d060c291915dd681e4c0869d521052eb7519ce2a7819095dc4c26d485265"},"schema_version":"1.0","source":{"id":"2401.10465","kind":"arxiv","version":1}},"canonical_sha256":"63c6ec04fa63cd11871d07aa7ebc6612ccee7956bb769608abb588445d0eaace","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63c6ec04fa63cd11871d07aa7ebc6612ccee7956bb769608abb588445d0eaace","first_computed_at":"2026-07-05T07:35:26.726190Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:35:26.726190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6RRnfP/JJ/GvmhFJSkhLZmKz/Zbt+wuXkfDcCQgFc0d9ZBcBLI9bjN8OC/Vo5bVxat3vzJgrTbX28LVw6+VAAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:35:26.726707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.10465","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88126529a9cbdb15ebbe098b05f47aae9f48515c4bdd8e1859fd264cfdcf9ff7","sha256:c526ad85188b6cccbaed1e24b1a772f2fcc593d038f566f3bc4e4c59d4189b3f"],"state_sha256":"7b8edc17de9686fc5395fc2742f8178c7775c2718e14fda9bf5eb57e82633322"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M7mNvbLZmuyV8sNlRPw/FtB5/BA1PSQ2XsIVF9wcdLxfx9FGmEFolWtkQ9pot2G15Gvv5IB1D7WAbRrlI1LqDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T11:48:47.932664Z","bundle_sha256":"8e5abba508a9fb9fb9a69cb5d77049183818e03aaef0343d37e2afc886726f5a"}}