{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NWGFCLLMEFBYVEYJEWPHLFD4V7","short_pith_number":"pith:NWGFCLLM","schema_version":"1.0","canonical_sha256":"6d8c512d6c21438a9309259e75947cafd034babc170c3c5494b7cdfa812efcfb","source":{"kind":"arxiv","id":"2405.16677","version":2},"attestation_state":"computed","paper":{"title":"Crossmodal ASR Error Correction with Discrete Speech Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Catherine Lai, Peter Bell, Pinzhen Chen, Yuanchao Li","submitted_at":"2024-05-26T19:58:38Z","abstract_excerpt":"ASR remains unsatisfactory in scenarios where the speaking style diverges from that used to train ASR systems, resulting in erroneous transcripts. To address this, ASR Error Correction (AEC), a post-ASR processing approach, is required. In this work, we tackle an understudied issue: the Low-Resource Out-of-Domain (LROOD) problem, by investigating crossmodal AEC on very limited downstream data with 1-best hypothesis transcription. We explore pre-training and fine-tuning strategies and uncover an ASR domain discrepancy phenomenon, shedding light on appropriate training schemes for LROOD data. Mo"},"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":"2405.16677","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-05-26T19:58:38Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"355472c45273b52ec014acececdda056915b78a9b0e49fd59e435a7a4f915afc","abstract_canon_sha256":"5cad65a86024675040bc9a4a0aebac395d2abf730bfc1298d8bd26afe0eae699"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:26.312683Z","signature_b64":"9sCRZx/EPIqzkCTljZyekjK0OkgM0gUP9h6TzReIEEf8jKb82K9z7PDdg8+vuaakPR4UpZ5ZS84pX/yAvRXfCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d8c512d6c21438a9309259e75947cafd034babc170c3c5494b7cdfa812efcfb","last_reissued_at":"2026-07-05T09:06:26.312123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:26.312123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Crossmodal ASR Error Correction with Discrete Speech Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Catherine Lai, Peter Bell, Pinzhen Chen, Yuanchao Li","submitted_at":"2024-05-26T19:58:38Z","abstract_excerpt":"ASR remains unsatisfactory in scenarios where the speaking style diverges from that used to train ASR systems, resulting in erroneous transcripts. To address this, ASR Error Correction (AEC), a post-ASR processing approach, is required. In this work, we tackle an understudied issue: the Low-Resource Out-of-Domain (LROOD) problem, by investigating crossmodal AEC on very limited downstream data with 1-best hypothesis transcription. We explore pre-training and fine-tuning strategies and uncover an ASR domain discrepancy phenomenon, shedding light on appropriate training schemes for LROOD data. Mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16677","kind":"arxiv","version":2},"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/2405.16677/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":"2405.16677","created_at":"2026-07-05T09:06:26.312190+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16677v2","created_at":"2026-07-05T09:06:26.312190+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16677","created_at":"2026-07-05T09:06:26.312190+00:00"},{"alias_kind":"pith_short_12","alias_value":"NWGFCLLMEFBY","created_at":"2026-07-05T09:06:26.312190+00:00"},{"alias_kind":"pith_short_16","alias_value":"NWGFCLLMEFBYVEYJ","created_at":"2026-07-05T09:06:26.312190+00:00"},{"alias_kind":"pith_short_8","alias_value":"NWGFCLLM","created_at":"2026-07-05T09:06:26.312190+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04357","citing_title":"PARCO: Phoneme-Augmented Robust Contextual ASR via Contrastive Entity Disambiguation","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NWGFCLLMEFBYVEYJEWPHLFD4V7","json":"https://pith.science/pith/NWGFCLLMEFBYVEYJEWPHLFD4V7.json","graph_json":"https://pith.science/api/pith-number/NWGFCLLMEFBYVEYJEWPHLFD4V7/graph.json","events_json":"https://pith.science/api/pith-number/NWGFCLLMEFBYVEYJEWPHLFD4V7/events.json","paper":"https://pith.science/paper/NWGFCLLM"},"agent_actions":{"view_html":"https://pith.science/pith/NWGFCLLMEFBYVEYJEWPHLFD4V7","download_json":"https://pith.science/pith/NWGFCLLMEFBYVEYJEWPHLFD4V7.json","view_paper":"https://pith.science/paper/NWGFCLLM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16677&json=true","fetch_graph":"https://pith.science/api/pith-number/NWGFCLLMEFBYVEYJEWPHLFD4V7/graph.json","fetch_events":"https://pith.science/api/pith-number/NWGFCLLMEFBYVEYJEWPHLFD4V7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NWGFCLLMEFBYVEYJEWPHLFD4V7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NWGFCLLMEFBYVEYJEWPHLFD4V7/action/storage_attestation","attest_author":"https://pith.science/pith/NWGFCLLMEFBYVEYJEWPHLFD4V7/action/author_attestation","sign_citation":"https://pith.science/pith/NWGFCLLMEFBYVEYJEWPHLFD4V7/action/citation_signature","submit_replication":"https://pith.science/pith/NWGFCLLMEFBYVEYJEWPHLFD4V7/action/replication_record"}},"created_at":"2026-07-05T09:06:26.312190+00:00","updated_at":"2026-07-05T09:06:26.312190+00:00"}