{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UTOWSQAUI2NDS3ZYOIHUYTRQ3U","short_pith_number":"pith:UTOWSQAU","schema_version":"1.0","canonical_sha256":"a4dd694014469a396f38720f4c4e30dd314b83c57ed8453acfbc07fa63f0543f","source":{"kind":"arxiv","id":"2309.10917","version":1},"attestation_state":"computed","paper":{"title":"End-to-End Speech Recognition Contextualization with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Christian Fuegen, Chunyang Wu, Egor Lakomkin, Michael L. Seltzer, Ozlem Kalinli, Yassir Fathullah","submitted_at":"2023-09-19T20:28:57Z","abstract_excerpt":"In recent years, Large Language Models (LLMs) have garnered significant attention from the research community due to their exceptional performance and generalization capabilities. In this paper, we introduce a novel method for contextualizing speech recognition models incorporating LLMs. Our approach casts speech recognition as a mixed-modal language modeling task based on a pretrained LLM. We provide audio features, along with optional text tokens for context, to train the system to complete transcriptions in a decoder-only fashion. As a result, the system is implicitly incentivized to learn "},"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":"2309.10917","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-19T20:28:57Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"f5e545f9e4dfd48d7aa1e89597693af0c5beaeade821a192b817a65ad2d30b66","abstract_canon_sha256":"608a2f62a3f6c5e5e639c4ed2f154a53572221142099d5d7bc0270122dd90800"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:28.488227Z","signature_b64":"d5hOFofeC33GrRIC8GVbNU8MS3E/Bem3cI17o8TIkPHZaQWlQ1qFGWRtGFU5XQ1kgpsjML7XOu0JPHZdnUm4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4dd694014469a396f38720f4c4e30dd314b83c57ed8453acfbc07fa63f0543f","last_reissued_at":"2026-07-05T06:52:28.487737Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:28.487737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Speech Recognition Contextualization with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Christian Fuegen, Chunyang Wu, Egor Lakomkin, Michael L. Seltzer, Ozlem Kalinli, Yassir Fathullah","submitted_at":"2023-09-19T20:28:57Z","abstract_excerpt":"In recent years, Large Language Models (LLMs) have garnered significant attention from the research community due to their exceptional performance and generalization capabilities. In this paper, we introduce a novel method for contextualizing speech recognition models incorporating LLMs. Our approach casts speech recognition as a mixed-modal language modeling task based on a pretrained LLM. We provide audio features, along with optional text tokens for context, to train the system to complete transcriptions in a decoder-only fashion. As a result, the system is implicitly incentivized to learn "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10917","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/2309.10917/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":"2309.10917","created_at":"2026-07-05T06:52:28.487793+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.10917v1","created_at":"2026-07-05T06:52:28.487793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10917","created_at":"2026-07-05T06:52:28.487793+00:00"},{"alias_kind":"pith_short_12","alias_value":"UTOWSQAUI2ND","created_at":"2026-07-05T06:52:28.487793+00:00"},{"alias_kind":"pith_short_16","alias_value":"UTOWSQAUI2NDS3ZY","created_at":"2026-07-05T06:52:28.487793+00:00"},{"alias_kind":"pith_short_8","alias_value":"UTOWSQAU","created_at":"2026-07-05T06:52:28.487793+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08486","citing_title":"TRADE: Transducer-Augmented Decoder for Speech LLM","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UTOWSQAUI2NDS3ZYOIHUYTRQ3U","json":"https://pith.science/pith/UTOWSQAUI2NDS3ZYOIHUYTRQ3U.json","graph_json":"https://pith.science/api/pith-number/UTOWSQAUI2NDS3ZYOIHUYTRQ3U/graph.json","events_json":"https://pith.science/api/pith-number/UTOWSQAUI2NDS3ZYOIHUYTRQ3U/events.json","paper":"https://pith.science/paper/UTOWSQAU"},"agent_actions":{"view_html":"https://pith.science/pith/UTOWSQAUI2NDS3ZYOIHUYTRQ3U","download_json":"https://pith.science/pith/UTOWSQAUI2NDS3ZYOIHUYTRQ3U.json","view_paper":"https://pith.science/paper/UTOWSQAU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.10917&json=true","fetch_graph":"https://pith.science/api/pith-number/UTOWSQAUI2NDS3ZYOIHUYTRQ3U/graph.json","fetch_events":"https://pith.science/api/pith-number/UTOWSQAUI2NDS3ZYOIHUYTRQ3U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UTOWSQAUI2NDS3ZYOIHUYTRQ3U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UTOWSQAUI2NDS3ZYOIHUYTRQ3U/action/storage_attestation","attest_author":"https://pith.science/pith/UTOWSQAUI2NDS3ZYOIHUYTRQ3U/action/author_attestation","sign_citation":"https://pith.science/pith/UTOWSQAUI2NDS3ZYOIHUYTRQ3U/action/citation_signature","submit_replication":"https://pith.science/pith/UTOWSQAUI2NDS3ZYOIHUYTRQ3U/action/replication_record"}},"created_at":"2026-07-05T06:52:28.487793+00:00","updated_at":"2026-07-05T06:52:28.487793+00:00"}