{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GCYUNAAV2S75V367WMPOMY5DMT","short_pith_number":"pith:GCYUNAAV","schema_version":"1.0","canonical_sha256":"30b1468015d4bfdaefdfb31ee663a364efb82981c25593946d7f9ebd9308406f","source":{"kind":"arxiv","id":"2401.10446","version":1},"attestation_state":"computed","paper":{"title":"Large Language Models are Efficient Learners of Noise-Robust Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chao-Han Huck Yang, Chao Zhang, Chen Chen, EnSiong Chng, Pin-Yu Chen, Ruizhe Li, Yuchen Hu","submitted_at":"2024-01-19T01:29:27Z","abstract_excerpt":"Recent advances in large language models (LLMs) have promoted generative error correction (GER) for automatic speech recognition (ASR), which leverages the rich linguistic knowledge and powerful reasoning ability of LLMs to improve recognition results. The latest work proposes a GER benchmark with HyPoradise dataset to learn the mapping from ASR N-best hypotheses to ground-truth transcription by efficient LLM finetuning, which shows great effectiveness but lacks specificity on noise-robust ASR. In this work, we extend the benchmark to noisy conditions and investigate if we can teach LLMs to pe"},"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":"2401.10446","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-19T01:29:27Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"c2ddd5b0c96aa8bec810db97058aadceffd987479ed0f67117e30e5b77f23991","abstract_canon_sha256":"7e32ef5e59a911928dac6018cd5a6bd6f4b24356d9088d39e756a1f2697f626b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:26.275594Z","signature_b64":"KciLpSJIy3QIvtxErEHM796NHdpXEuGk2whSoaguAkz7MPn2tPiHgIsacZcyEKBhXd8AoAcGCyGHTXNvNsRFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30b1468015d4bfdaefdfb31ee663a364efb82981c25593946d7f9ebd9308406f","last_reissued_at":"2026-07-05T07:35:26.275194Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:26.275194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models are Efficient Learners of Noise-Robust Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chao-Han Huck Yang, Chao Zhang, Chen Chen, EnSiong Chng, Pin-Yu Chen, Ruizhe Li, Yuchen Hu","submitted_at":"2024-01-19T01:29:27Z","abstract_excerpt":"Recent advances in large language models (LLMs) have promoted generative error correction (GER) for automatic speech recognition (ASR), which leverages the rich linguistic knowledge and powerful reasoning ability of LLMs to improve recognition results. The latest work proposes a GER benchmark with HyPoradise dataset to learn the mapping from ASR N-best hypotheses to ground-truth transcription by efficient LLM finetuning, which shows great effectiveness but lacks specificity on noise-robust ASR. In this work, we extend the benchmark to noisy conditions and investigate if we can teach LLMs to pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10446","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/2401.10446/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":"2401.10446","created_at":"2026-07-05T07:35:26.275251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.10446v1","created_at":"2026-07-05T07:35:26.275251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10446","created_at":"2026-07-05T07:35:26.275251+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCYUNAAV2S75","created_at":"2026-07-05T07:35:26.275251+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCYUNAAV2S75V367","created_at":"2026-07-05T07:35:26.275251+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCYUNAAV","created_at":"2026-07-05T07:35:26.275251+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22005","citing_title":"Leveraging LLM for Stuttering Speech: A Unified Architecture Bridging Recognition and Event Detection","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GCYUNAAV2S75V367WMPOMY5DMT","json":"https://pith.science/pith/GCYUNAAV2S75V367WMPOMY5DMT.json","graph_json":"https://pith.science/api/pith-number/GCYUNAAV2S75V367WMPOMY5DMT/graph.json","events_json":"https://pith.science/api/pith-number/GCYUNAAV2S75V367WMPOMY5DMT/events.json","paper":"https://pith.science/paper/GCYUNAAV"},"agent_actions":{"view_html":"https://pith.science/pith/GCYUNAAV2S75V367WMPOMY5DMT","download_json":"https://pith.science/pith/GCYUNAAV2S75V367WMPOMY5DMT.json","view_paper":"https://pith.science/paper/GCYUNAAV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.10446&json=true","fetch_graph":"https://pith.science/api/pith-number/GCYUNAAV2S75V367WMPOMY5DMT/graph.json","fetch_events":"https://pith.science/api/pith-number/GCYUNAAV2S75V367WMPOMY5DMT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCYUNAAV2S75V367WMPOMY5DMT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCYUNAAV2S75V367WMPOMY5DMT/action/storage_attestation","attest_author":"https://pith.science/pith/GCYUNAAV2S75V367WMPOMY5DMT/action/author_attestation","sign_citation":"https://pith.science/pith/GCYUNAAV2S75V367WMPOMY5DMT/action/citation_signature","submit_replication":"https://pith.science/pith/GCYUNAAV2S75V367WMPOMY5DMT/action/replication_record"}},"created_at":"2026-07-05T07:35:26.275251+00:00","updated_at":"2026-07-05T07:35:26.275251+00:00"}