{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YO4JVHB4Y77B66CK3H5AD4A7KJ","short_pith_number":"pith:YO4JVHB4","schema_version":"1.0","canonical_sha256":"c3b89a9c3cc7fe1f784ad9fa01f01f5250a2a09eaee6ad768a051bd341a1deee","source":{"kind":"arxiv","id":"2104.04091","version":1},"attestation_state":"computed","paper":{"title":"Grapheme-to-Phoneme Transformer Model for Transfer Learning Dialects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"cs.CL","authors_text":"Eric Engelhart, Gaurav Bharaj, Mahsa Elyasi","submitted_at":"2021-04-08T21:36:21Z","abstract_excerpt":"Grapheme-to-Phoneme (G2P) models convert words to their phonetic pronunciations. Classic G2P methods include rule-based systems and pronunciation dictionaries, while modern G2P systems incorporate learning, such as, LSTM and Transformer-based attention models. Usually, dictionary-based methods require significant manual effort to build, and have limited adaptivity on unseen words. And transformer-based models require significant training data, and do not generalize well, especially for dialects with limited data.\n  We propose a novel use of transformer-based attention model that can adapt to u"},"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":"2104.04091","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-08T21:36:21Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"dc49c52c9ed5cfdb2b6a262f05d7138e30659e05a67cb6f45cbbd5a5462a4b9c","abstract_canon_sha256":"4fb9b31c8072a898cede4a8cf07c5aee06936903d364f5c18e1821640d65055c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:34.846261Z","signature_b64":"8236kEPnjqUOmQgI/5SnchJsOY1AaHQK1+jP6XJXiUpN7OLc6m3knmRaxNSXgm0+ZZjZxSmgYSIwQulJusx2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3b89a9c3cc7fe1f784ad9fa01f01f5250a2a09eaee6ad768a051bd341a1deee","last_reissued_at":"2026-07-05T02:30:34.845817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:34.845817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grapheme-to-Phoneme Transformer Model for Transfer Learning Dialects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"cs.CL","authors_text":"Eric Engelhart, Gaurav Bharaj, Mahsa Elyasi","submitted_at":"2021-04-08T21:36:21Z","abstract_excerpt":"Grapheme-to-Phoneme (G2P) models convert words to their phonetic pronunciations. Classic G2P methods include rule-based systems and pronunciation dictionaries, while modern G2P systems incorporate learning, such as, LSTM and Transformer-based attention models. Usually, dictionary-based methods require significant manual effort to build, and have limited adaptivity on unseen words. And transformer-based models require significant training data, and do not generalize well, especially for dialects with limited data.\n  We propose a novel use of transformer-based attention model that can adapt to u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04091","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/2104.04091/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":"2104.04091","created_at":"2026-07-05T02:30:34.845883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.04091v1","created_at":"2026-07-05T02:30:34.845883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04091","created_at":"2026-07-05T02:30:34.845883+00:00"},{"alias_kind":"pith_short_12","alias_value":"YO4JVHB4Y77B","created_at":"2026-07-05T02:30:34.845883+00:00"},{"alias_kind":"pith_short_16","alias_value":"YO4JVHB4Y77B66CK","created_at":"2026-07-05T02:30:34.845883+00:00"},{"alias_kind":"pith_short_8","alias_value":"YO4JVHB4","created_at":"2026-07-05T02:30:34.845883+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/YO4JVHB4Y77B66CK3H5AD4A7KJ","json":"https://pith.science/pith/YO4JVHB4Y77B66CK3H5AD4A7KJ.json","graph_json":"https://pith.science/api/pith-number/YO4JVHB4Y77B66CK3H5AD4A7KJ/graph.json","events_json":"https://pith.science/api/pith-number/YO4JVHB4Y77B66CK3H5AD4A7KJ/events.json","paper":"https://pith.science/paper/YO4JVHB4"},"agent_actions":{"view_html":"https://pith.science/pith/YO4JVHB4Y77B66CK3H5AD4A7KJ","download_json":"https://pith.science/pith/YO4JVHB4Y77B66CK3H5AD4A7KJ.json","view_paper":"https://pith.science/paper/YO4JVHB4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.04091&json=true","fetch_graph":"https://pith.science/api/pith-number/YO4JVHB4Y77B66CK3H5AD4A7KJ/graph.json","fetch_events":"https://pith.science/api/pith-number/YO4JVHB4Y77B66CK3H5AD4A7KJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YO4JVHB4Y77B66CK3H5AD4A7KJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YO4JVHB4Y77B66CK3H5AD4A7KJ/action/storage_attestation","attest_author":"https://pith.science/pith/YO4JVHB4Y77B66CK3H5AD4A7KJ/action/author_attestation","sign_citation":"https://pith.science/pith/YO4JVHB4Y77B66CK3H5AD4A7KJ/action/citation_signature","submit_replication":"https://pith.science/pith/YO4JVHB4Y77B66CK3H5AD4A7KJ/action/replication_record"}},"created_at":"2026-07-05T02:30:34.845883+00:00","updated_at":"2026-07-05T02:30:34.845883+00:00"}