{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DNUMMI6RWWXKOG4HHT3YUFWMQ7","short_pith_number":"pith:DNUMMI6R","schema_version":"1.0","canonical_sha256":"1b68c623d1b5aea71b873cf78a16cc87cfc239c56b032a21f70b80c0ebf65f50","source":{"kind":"arxiv","id":"2203.14222","version":2},"attestation_state":"computed","paper":{"title":"Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Guan-Ting Lin, Hung-yi Lee, Shang-Wen Li","submitted_at":"2022-03-27T06:38:39Z","abstract_excerpt":"Although deep learning-based end-to-end Automatic Speech Recognition (ASR) has shown remarkable performance in recent years, it suffers severe performance regression on test samples drawn from different data distributions. Test-time Adaptation (TTA), previously explored in the computer vision area, aims to adapt the model trained on source domains to yield better predictions for test samples, often out-of-domain, without accessing the source data. Here, we propose the Single-Utterance Test-time Adaptation (SUTA) framework for ASR, which is the first TTA study on ASR to our best knowledge. The "},"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":"2203.14222","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-03-27T06:38:39Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"dc2eb833661868765480a58a1924d661cb8e27b1eaf1b24151e52cfab062dd2e","abstract_canon_sha256":"89900bc931b3917da03a0fdcf16247d6695b6d9a0bcc72f4ae431e344f0c9acb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:33:33.807647Z","signature_b64":"48ZljBRa7j4Sj0x/yIWVsxxmmCnDD+m9P62Rswe/wQHryRiSusOR49XExyp7A/jPikI56DGq0v1qnkehM4IGAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b68c623d1b5aea71b873cf78a16cc87cfc239c56b032a21f70b80c0ebf65f50","last_reissued_at":"2026-07-05T04:33:33.807152Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:33:33.807152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Guan-Ting Lin, Hung-yi Lee, Shang-Wen Li","submitted_at":"2022-03-27T06:38:39Z","abstract_excerpt":"Although deep learning-based end-to-end Automatic Speech Recognition (ASR) has shown remarkable performance in recent years, it suffers severe performance regression on test samples drawn from different data distributions. Test-time Adaptation (TTA), previously explored in the computer vision area, aims to adapt the model trained on source domains to yield better predictions for test samples, often out-of-domain, without accessing the source data. Here, we propose the Single-Utterance Test-time Adaptation (SUTA) framework for ASR, which is the first TTA study on ASR to our best knowledge. The "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.14222","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/2203.14222/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":"2203.14222","created_at":"2026-07-05T04:33:33.807209+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.14222v2","created_at":"2026-07-05T04:33:33.807209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.14222","created_at":"2026-07-05T04:33:33.807209+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNUMMI6RWWXK","created_at":"2026-07-05T04:33:33.807209+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNUMMI6RWWXKOG4H","created_at":"2026-07-05T04:33:33.807209+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNUMMI6R","created_at":"2026-07-05T04:33:33.807209+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15523","citing_title":"An Investigation of Test-time Adaptation for Audio Classification under Background Noise","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DNUMMI6RWWXKOG4HHT3YUFWMQ7","json":"https://pith.science/pith/DNUMMI6RWWXKOG4HHT3YUFWMQ7.json","graph_json":"https://pith.science/api/pith-number/DNUMMI6RWWXKOG4HHT3YUFWMQ7/graph.json","events_json":"https://pith.science/api/pith-number/DNUMMI6RWWXKOG4HHT3YUFWMQ7/events.json","paper":"https://pith.science/paper/DNUMMI6R"},"agent_actions":{"view_html":"https://pith.science/pith/DNUMMI6RWWXKOG4HHT3YUFWMQ7","download_json":"https://pith.science/pith/DNUMMI6RWWXKOG4HHT3YUFWMQ7.json","view_paper":"https://pith.science/paper/DNUMMI6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.14222&json=true","fetch_graph":"https://pith.science/api/pith-number/DNUMMI6RWWXKOG4HHT3YUFWMQ7/graph.json","fetch_events":"https://pith.science/api/pith-number/DNUMMI6RWWXKOG4HHT3YUFWMQ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNUMMI6RWWXKOG4HHT3YUFWMQ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNUMMI6RWWXKOG4HHT3YUFWMQ7/action/storage_attestation","attest_author":"https://pith.science/pith/DNUMMI6RWWXKOG4HHT3YUFWMQ7/action/author_attestation","sign_citation":"https://pith.science/pith/DNUMMI6RWWXKOG4HHT3YUFWMQ7/action/citation_signature","submit_replication":"https://pith.science/pith/DNUMMI6RWWXKOG4HHT3YUFWMQ7/action/replication_record"}},"created_at":"2026-07-05T04:33:33.807209+00:00","updated_at":"2026-07-05T04:33:33.807209+00:00"}