{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MPDOYBH2MPGRDBY5A6VH5PDGCL","short_pith_number":"pith:MPDOYBH2","schema_version":"1.0","canonical_sha256":"63c6ec04fa63cd11871d07aa7ebc6612ccee7956bb769608abb588445d0eaace","source":{"kind":"arxiv","id":"2401.10465","version":1},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.10465","created_at":"2026-07-05T07:35:26.726250+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.10465v1","created_at":"2026-07-05T07:35:26.726250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10465","created_at":"2026-07-05T07:35:26.726250+00:00"},{"alias_kind":"pith_short_12","alias_value":"MPDOYBH2MPGR","created_at":"2026-07-05T07:35:26.726250+00:00"},{"alias_kind":"pith_short_16","alias_value":"MPDOYBH2MPGRDBY5","created_at":"2026-07-05T07:35:26.726250+00:00"},{"alias_kind":"pith_short_8","alias_value":"MPDOYBH2","created_at":"2026-07-05T07:35:26.726250+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/MPDOYBH2MPGRDBY5A6VH5PDGCL","json":"https://pith.science/pith/MPDOYBH2MPGRDBY5A6VH5PDGCL.json","graph_json":"https://pith.science/api/pith-number/MPDOYBH2MPGRDBY5A6VH5PDGCL/graph.json","events_json":"https://pith.science/api/pith-number/MPDOYBH2MPGRDBY5A6VH5PDGCL/events.json","paper":"https://pith.science/paper/MPDOYBH2"},"agent_actions":{"view_html":"https://pith.science/pith/MPDOYBH2MPGRDBY5A6VH5PDGCL","download_json":"https://pith.science/pith/MPDOYBH2MPGRDBY5A6VH5PDGCL.json","view_paper":"https://pith.science/paper/MPDOYBH2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.10465&json=true","fetch_graph":"https://pith.science/api/pith-number/MPDOYBH2MPGRDBY5A6VH5PDGCL/graph.json","fetch_events":"https://pith.science/api/pith-number/MPDOYBH2MPGRDBY5A6VH5PDGCL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MPDOYBH2MPGRDBY5A6VH5PDGCL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MPDOYBH2MPGRDBY5A6VH5PDGCL/action/storage_attestation","attest_author":"https://pith.science/pith/MPDOYBH2MPGRDBY5A6VH5PDGCL/action/author_attestation","sign_citation":"https://pith.science/pith/MPDOYBH2MPGRDBY5A6VH5PDGCL/action/citation_signature","submit_replication":"https://pith.science/pith/MPDOYBH2MPGRDBY5A6VH5PDGCL/action/replication_record"}},"created_at":"2026-07-05T07:35:26.726250+00:00","updated_at":"2026-07-05T07:35:26.726250+00:00"}