{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JXNCZBEN6LRUU2VM4W4UDYRHOM","short_pith_number":"pith:JXNCZBEN","schema_version":"1.0","canonical_sha256":"4dda2c848df2e34a6aace5b941e2277332d5f4a1e2783e241750435a2648feaa","source":{"kind":"arxiv","id":"2409.08554","version":1},"attestation_state":"computed","paper":{"title":"LLM-Powered Grapheme-to-Phoneme Conversion: Benchmark and Case Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hamid R. Rabiee, Mahta Fetrat Qharabagh, Zahra Dehghanian","submitted_at":"2024-09-13T06:13:55Z","abstract_excerpt":"Grapheme-to-phoneme (G2P) conversion is critical in speech processing, particularly for applications like speech synthesis. G2P systems must possess linguistic understanding and contextual awareness of languages with polyphone words and context-dependent phonemes. Large language models (LLMs) have recently demonstrated significant potential in various language tasks, suggesting that their phonetic knowledge could be leveraged for G2P. In this paper, we evaluate the performance of LLMs in G2P conversion and introduce prompting and post-processing methods that enhance LLM outputs without additio"},"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":"2409.08554","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-13T06:13:55Z","cross_cats_sorted":[],"title_canon_sha256":"a6b905f7412a2498e4d60c1170637419c5793e01c40d0f0ee9d09809a05c0e2f","abstract_canon_sha256":"209015daa5ebadb318b07eb0c5533ef1ab084b238c5072813eb82c1bf9e806fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:33.078979Z","signature_b64":"Cq81QJ6ejZ9Rpc5QJKQoc8vDPV6sPdu4iezwm8RaFpiPataSACHpDN9UXlTVtLIxqU2BVutHIfdMupTGckzZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4dda2c848df2e34a6aace5b941e2277332d5f4a1e2783e241750435a2648feaa","last_reissued_at":"2026-07-05T09:06:33.078556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:33.078556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Powered Grapheme-to-Phoneme Conversion: Benchmark and Case Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hamid R. Rabiee, Mahta Fetrat Qharabagh, Zahra Dehghanian","submitted_at":"2024-09-13T06:13:55Z","abstract_excerpt":"Grapheme-to-phoneme (G2P) conversion is critical in speech processing, particularly for applications like speech synthesis. G2P systems must possess linguistic understanding and contextual awareness of languages with polyphone words and context-dependent phonemes. Large language models (LLMs) have recently demonstrated significant potential in various language tasks, suggesting that their phonetic knowledge could be leveraged for G2P. In this paper, we evaluate the performance of LLMs in G2P conversion and introduce prompting and post-processing methods that enhance LLM outputs without additio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08554","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/2409.08554/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":"2409.08554","created_at":"2026-07-05T09:06:33.078611+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.08554v1","created_at":"2026-07-05T09:06:33.078611+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08554","created_at":"2026-07-05T09:06:33.078611+00:00"},{"alias_kind":"pith_short_12","alias_value":"JXNCZBEN6LRU","created_at":"2026-07-05T09:06:33.078611+00:00"},{"alias_kind":"pith_short_16","alias_value":"JXNCZBEN6LRUU2VM","created_at":"2026-07-05T09:06:33.078611+00:00"},{"alias_kind":"pith_short_8","alias_value":"JXNCZBEN","created_at":"2026-07-05T09:06:33.078611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22009","citing_title":"Benchmarking Large Language Models for Grapheme-to-Phoneme Conversion: A Japanese Case Study","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20086","citing_title":"OLaPh: Optimal Language Phonemizer","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17105","citing_title":"How Tokenization Limits Phonological Knowledge Representation in Language Models and How to Improve Them","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JXNCZBEN6LRUU2VM4W4UDYRHOM","json":"https://pith.science/pith/JXNCZBEN6LRUU2VM4W4UDYRHOM.json","graph_json":"https://pith.science/api/pith-number/JXNCZBEN6LRUU2VM4W4UDYRHOM/graph.json","events_json":"https://pith.science/api/pith-number/JXNCZBEN6LRUU2VM4W4UDYRHOM/events.json","paper":"https://pith.science/paper/JXNCZBEN"},"agent_actions":{"view_html":"https://pith.science/pith/JXNCZBEN6LRUU2VM4W4UDYRHOM","download_json":"https://pith.science/pith/JXNCZBEN6LRUU2VM4W4UDYRHOM.json","view_paper":"https://pith.science/paper/JXNCZBEN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.08554&json=true","fetch_graph":"https://pith.science/api/pith-number/JXNCZBEN6LRUU2VM4W4UDYRHOM/graph.json","fetch_events":"https://pith.science/api/pith-number/JXNCZBEN6LRUU2VM4W4UDYRHOM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JXNCZBEN6LRUU2VM4W4UDYRHOM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JXNCZBEN6LRUU2VM4W4UDYRHOM/action/storage_attestation","attest_author":"https://pith.science/pith/JXNCZBEN6LRUU2VM4W4UDYRHOM/action/author_attestation","sign_citation":"https://pith.science/pith/JXNCZBEN6LRUU2VM4W4UDYRHOM/action/citation_signature","submit_replication":"https://pith.science/pith/JXNCZBEN6LRUU2VM4W4UDYRHOM/action/replication_record"}},"created_at":"2026-07-05T09:06:33.078611+00:00","updated_at":"2026-07-05T09:06:33.078611+00:00"}