{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YR3IDB7IWJVPT7QO4QFJKJRER6","short_pith_number":"pith:YR3IDB7I","schema_version":"1.0","canonical_sha256":"c4768187e8b26af9fe0ee40a9526248faa99b00f5af9ca79ad26dfbd056ab6f0","source":{"kind":"arxiv","id":"2401.05689","version":1},"attestation_state":"computed","paper":{"title":"UCorrect: An Unsupervised Framework for Automatic Speech Recognition Error Correction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chang Su, Daimeng Wei, Hao Yang, Hengchao Shang, Jiaxin Guo, Minghan Wang, Min Zhang, Shimin Tao, Xiaosong Qiao, Yinglu Li, Zhengzhe Yu, Zongyao Li","submitted_at":"2024-01-11T06:30:07Z","abstract_excerpt":"Error correction techniques have been used to refine the output sentences from automatic speech recognition (ASR) models and achieve a lower word error rate (WER). Previous works usually adopt end-to-end models and has strong dependency on Pseudo Paired Data and Original Paired Data. But when only pre-training on Pseudo Paired Data, previous models have negative effect on correction. While fine-tuning on Original Paired Data, the source side data must be transcribed by a well-trained ASR model, which takes a lot of time and not universal. In this paper, we propose UCorrect, an unsupervised Det"},"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":"2401.05689","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-11T06:30:07Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"00a396a6957bd724e53e3be29d47ce3678459af853d0c2c93bba03ba1792bdcf","abstract_canon_sha256":"89f8203c27a45cc6f86ea8457759e17b2780cff30b529b4e162ef7f347b42c74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:34.063602Z","signature_b64":"Adin9Xul1CwKWXOVJtxZXBJQeQVBzSjut5qjtRJK+5OxCZAvisTI05V+cV4ZAlwsZcSPZJJUZHTUEs/tMysyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4768187e8b26af9fe0ee40a9526248faa99b00f5af9ca79ad26dfbd056ab6f0","last_reissued_at":"2026-07-05T07:32:34.063087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:34.063087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UCorrect: An Unsupervised Framework for Automatic Speech Recognition Error Correction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chang Su, Daimeng Wei, Hao Yang, Hengchao Shang, Jiaxin Guo, Minghan Wang, Min Zhang, Shimin Tao, Xiaosong Qiao, Yinglu Li, Zhengzhe Yu, Zongyao Li","submitted_at":"2024-01-11T06:30:07Z","abstract_excerpt":"Error correction techniques have been used to refine the output sentences from automatic speech recognition (ASR) models and achieve a lower word error rate (WER). Previous works usually adopt end-to-end models and has strong dependency on Pseudo Paired Data and Original Paired Data. But when only pre-training on Pseudo Paired Data, previous models have negative effect on correction. While fine-tuning on Original Paired Data, the source side data must be transcribed by a well-trained ASR model, which takes a lot of time and not universal. In this paper, we propose UCorrect, an unsupervised Det"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.05689","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/2401.05689/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":"2401.05689","created_at":"2026-07-05T07:32:34.063152+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.05689v1","created_at":"2026-07-05T07:32:34.063152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.05689","created_at":"2026-07-05T07:32:34.063152+00:00"},{"alias_kind":"pith_short_12","alias_value":"YR3IDB7IWJVP","created_at":"2026-07-05T07:32:34.063152+00:00"},{"alias_kind":"pith_short_16","alias_value":"YR3IDB7IWJVPT7QO","created_at":"2026-07-05T07:32:34.063152+00:00"},{"alias_kind":"pith_short_8","alias_value":"YR3IDB7I","created_at":"2026-07-05T07:32:34.063152+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/YR3IDB7IWJVPT7QO4QFJKJRER6","json":"https://pith.science/pith/YR3IDB7IWJVPT7QO4QFJKJRER6.json","graph_json":"https://pith.science/api/pith-number/YR3IDB7IWJVPT7QO4QFJKJRER6/graph.json","events_json":"https://pith.science/api/pith-number/YR3IDB7IWJVPT7QO4QFJKJRER6/events.json","paper":"https://pith.science/paper/YR3IDB7I"},"agent_actions":{"view_html":"https://pith.science/pith/YR3IDB7IWJVPT7QO4QFJKJRER6","download_json":"https://pith.science/pith/YR3IDB7IWJVPT7QO4QFJKJRER6.json","view_paper":"https://pith.science/paper/YR3IDB7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.05689&json=true","fetch_graph":"https://pith.science/api/pith-number/YR3IDB7IWJVPT7QO4QFJKJRER6/graph.json","fetch_events":"https://pith.science/api/pith-number/YR3IDB7IWJVPT7QO4QFJKJRER6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YR3IDB7IWJVPT7QO4QFJKJRER6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YR3IDB7IWJVPT7QO4QFJKJRER6/action/storage_attestation","attest_author":"https://pith.science/pith/YR3IDB7IWJVPT7QO4QFJKJRER6/action/author_attestation","sign_citation":"https://pith.science/pith/YR3IDB7IWJVPT7QO4QFJKJRER6/action/citation_signature","submit_replication":"https://pith.science/pith/YR3IDB7IWJVPT7QO4QFJKJRER6/action/replication_record"}},"created_at":"2026-07-05T07:32:34.063152+00:00","updated_at":"2026-07-05T07:32:34.063152+00:00"}