{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LG552UEVDW6TYNH7YRY3VVMQNI","short_pith_number":"pith:LG552UEV","schema_version":"1.0","canonical_sha256":"59bbdd50951dbd3c34ffc471bad5906a0bad16a3916f9981c489c40f200460f2","source":{"kind":"arxiv","id":"2309.10524","version":3},"attestation_state":"computed","paper":{"title":"Harnessing the Zero-Shot Power of Instruction-Tuned Large Language Model in End-to-End Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Tetsuji Ogawa, Tetsunori Kobayashi, Yosuke Higuchi","submitted_at":"2023-09-19T11:10:50Z","abstract_excerpt":"We propose to utilize an instruction-tuned large language model (LLM) for guiding the text generation process in automatic speech recognition (ASR). Modern large language models (LLMs) are adept at performing various text generation tasks through zero-shot learning, prompted with instructions designed for specific objectives. This paper explores the potential of LLMs to derive linguistic information that can facilitate text generation in end-to-end ASR models. Specifically, we instruct an LLM to correct grammatical errors in an ASR hypothesis and use the LLM-derived representations to refine t"},"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":"2309.10524","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-19T11:10:50Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"2d3ed88e3753ab5103b05d12215f2f6df323b1a97073d1ed94efc63cf5bf2fc1","abstract_canon_sha256":"dfe7dd90ee55b29be74724a5535aba153a4ef614acd1aa9cc92f5058479a79ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:37.836066Z","signature_b64":"ly33k7nINHNIYKBTaaTsnJaKtr1c24giAcEC92h8C5tRyqSq2kEEp26eMQ/oX8LBkTstyEBEkV2AtsABu0erBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59bbdd50951dbd3c34ffc471bad5906a0bad16a3916f9981c489c40f200460f2","last_reissued_at":"2026-07-05T09:57:37.835613Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:37.835613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harnessing the Zero-Shot Power of Instruction-Tuned Large Language Model in End-to-End Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Tetsuji Ogawa, Tetsunori Kobayashi, Yosuke Higuchi","submitted_at":"2023-09-19T11:10:50Z","abstract_excerpt":"We propose to utilize an instruction-tuned large language model (LLM) for guiding the text generation process in automatic speech recognition (ASR). Modern large language models (LLMs) are adept at performing various text generation tasks through zero-shot learning, prompted with instructions designed for specific objectives. This paper explores the potential of LLMs to derive linguistic information that can facilitate text generation in end-to-end ASR models. Specifically, we instruct an LLM to correct grammatical errors in an ASR hypothesis and use the LLM-derived representations to refine t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10524","kind":"arxiv","version":3},"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/2309.10524/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":"2309.10524","created_at":"2026-07-05T09:57:37.835676+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.10524v3","created_at":"2026-07-05T09:57:37.835676+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10524","created_at":"2026-07-05T09:57:37.835676+00:00"},{"alias_kind":"pith_short_12","alias_value":"LG552UEVDW6T","created_at":"2026-07-05T09:57:37.835676+00:00"},{"alias_kind":"pith_short_16","alias_value":"LG552UEVDW6TYNH7","created_at":"2026-07-05T09:57:37.835676+00:00"},{"alias_kind":"pith_short_8","alias_value":"LG552UEV","created_at":"2026-07-05T09:57:37.835676+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/LG552UEVDW6TYNH7YRY3VVMQNI","json":"https://pith.science/pith/LG552UEVDW6TYNH7YRY3VVMQNI.json","graph_json":"https://pith.science/api/pith-number/LG552UEVDW6TYNH7YRY3VVMQNI/graph.json","events_json":"https://pith.science/api/pith-number/LG552UEVDW6TYNH7YRY3VVMQNI/events.json","paper":"https://pith.science/paper/LG552UEV"},"agent_actions":{"view_html":"https://pith.science/pith/LG552UEVDW6TYNH7YRY3VVMQNI","download_json":"https://pith.science/pith/LG552UEVDW6TYNH7YRY3VVMQNI.json","view_paper":"https://pith.science/paper/LG552UEV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.10524&json=true","fetch_graph":"https://pith.science/api/pith-number/LG552UEVDW6TYNH7YRY3VVMQNI/graph.json","fetch_events":"https://pith.science/api/pith-number/LG552UEVDW6TYNH7YRY3VVMQNI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LG552UEVDW6TYNH7YRY3VVMQNI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LG552UEVDW6TYNH7YRY3VVMQNI/action/storage_attestation","attest_author":"https://pith.science/pith/LG552UEVDW6TYNH7YRY3VVMQNI/action/author_attestation","sign_citation":"https://pith.science/pith/LG552UEVDW6TYNH7YRY3VVMQNI/action/citation_signature","submit_replication":"https://pith.science/pith/LG552UEVDW6TYNH7YRY3VVMQNI/action/replication_record"}},"created_at":"2026-07-05T09:57:37.835676+00:00","updated_at":"2026-07-05T09:57:37.835676+00:00"}