{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:RESWJ7IKTP7T6CBAOJUKZV7WBE","short_pith_number":"pith:RESWJ7IK","schema_version":"1.0","canonical_sha256":"892564fd0a9bff3f08207268acd7f60904b47367033295ec22889cfaf4b8fcab","source":{"kind":"arxiv","id":"1708.01464","version":1},"attestation_state":"computed","paper":{"title":"Massively Multilingual Neural Grapheme-to-Phoneme Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ben Peters, Jon Dehdari, Josef van Genabith","submitted_at":"2017-08-04T11:57:02Z","abstract_excerpt":"Grapheme-to-phoneme conversion (g2p) is necessary for text-to-speech and automatic speech recognition systems. Most g2p systems are monolingual: they require language-specific data or handcrafting of rules. Such systems are difficult to extend to low resource languages, for which data and handcrafted rules are not available. As an alternative, we present a neural sequence-to-sequence approach to g2p which is trained on spelling--pronunciation pairs in hundreds of languages. The system shares a single encoder and decoder across all languages, allowing it to utilize the intrinsic similarities be"},"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":"1708.01464","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-04T11:57:02Z","cross_cats_sorted":[],"title_canon_sha256":"4bd090c817566b68c5a9d3aa386b95b85a70d12a71b8f178f74f5bc506791297","abstract_canon_sha256":"02f89227e0431e102439c90d99d6276475a90d035ab28e4556e4d36b60e65428"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:43.297073Z","signature_b64":"5A2mJ360RoP2H+FWdfyTPJjenLCxB97dG2RsLCC01Iyx68gPI43WVxs9Os6nNnJoeKVvyFIq95pO+61Had5cCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"892564fd0a9bff3f08207268acd7f60904b47367033295ec22889cfaf4b8fcab","last_reissued_at":"2026-05-18T00:33:43.296380Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:43.296380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Massively Multilingual Neural Grapheme-to-Phoneme Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ben Peters, Jon Dehdari, Josef van Genabith","submitted_at":"2017-08-04T11:57:02Z","abstract_excerpt":"Grapheme-to-phoneme conversion (g2p) is necessary for text-to-speech and automatic speech recognition systems. Most g2p systems are monolingual: they require language-specific data or handcrafting of rules. Such systems are difficult to extend to low resource languages, for which data and handcrafted rules are not available. As an alternative, we present a neural sequence-to-sequence approach to g2p which is trained on spelling--pronunciation pairs in hundreds of languages. The system shares a single encoder and decoder across all languages, allowing it to utilize the intrinsic similarities be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.01464","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":""},"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":"1708.01464","created_at":"2026-05-18T00:33:43.296514+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.01464v1","created_at":"2026-05-18T00:33:43.296514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.01464","created_at":"2026-05-18T00:33:43.296514+00:00"},{"alias_kind":"pith_short_12","alias_value":"RESWJ7IKTP7T","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"RESWJ7IKTP7T6CBA","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"RESWJ7IK","created_at":"2026-05-18T12:31:39.905425+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/RESWJ7IKTP7T6CBAOJUKZV7WBE","json":"https://pith.science/pith/RESWJ7IKTP7T6CBAOJUKZV7WBE.json","graph_json":"https://pith.science/api/pith-number/RESWJ7IKTP7T6CBAOJUKZV7WBE/graph.json","events_json":"https://pith.science/api/pith-number/RESWJ7IKTP7T6CBAOJUKZV7WBE/events.json","paper":"https://pith.science/paper/RESWJ7IK"},"agent_actions":{"view_html":"https://pith.science/pith/RESWJ7IKTP7T6CBAOJUKZV7WBE","download_json":"https://pith.science/pith/RESWJ7IKTP7T6CBAOJUKZV7WBE.json","view_paper":"https://pith.science/paper/RESWJ7IK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.01464&json=true","fetch_graph":"https://pith.science/api/pith-number/RESWJ7IKTP7T6CBAOJUKZV7WBE/graph.json","fetch_events":"https://pith.science/api/pith-number/RESWJ7IKTP7T6CBAOJUKZV7WBE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RESWJ7IKTP7T6CBAOJUKZV7WBE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RESWJ7IKTP7T6CBAOJUKZV7WBE/action/storage_attestation","attest_author":"https://pith.science/pith/RESWJ7IKTP7T6CBAOJUKZV7WBE/action/author_attestation","sign_citation":"https://pith.science/pith/RESWJ7IKTP7T6CBAOJUKZV7WBE/action/citation_signature","submit_replication":"https://pith.science/pith/RESWJ7IKTP7T6CBAOJUKZV7WBE/action/replication_record"}},"created_at":"2026-05-18T00:33:43.296514+00:00","updated_at":"2026-05-18T00:33:43.296514+00:00"}