{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6TMQESL5BRS5LQZALGHUZK55XA","short_pith_number":"pith:6TMQESL5","schema_version":"1.0","canonical_sha256":"f4d902497d0c65d5c320598f4cabbdb8311764bf738f53d278bec2b282d230e7","source":{"kind":"arxiv","id":"2011.13439","version":2},"attestation_state":"computed","paper":{"title":"Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jonathan Le Roux, Niko Moritz, Sameer Khurana, Takaaki Hori","submitted_at":"2020-11-26T18:51:26Z","abstract_excerpt":"The performance of automatic speech recognition (ASR) systems typically degrades significantly when the training and test data domains are mismatched. In this paper, we show that self-training (ST) combined with an uncertainty-based pseudo-label filtering approach can be effectively used for domain adaptation. We propose DUST, a dropout-based uncertainty-driven self-training technique which uses agreement between multiple predictions of an ASR system obtained for different dropout settings to measure the model's uncertainty about its prediction. DUST excludes pseudo-labeled data with high unce"},"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":"2011.13439","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-26T18:51:26Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"fdf170d059e0e6a6904a6894f7ef0ae564ffa2c14cc3aaf956cdc3e94cb45fed","abstract_canon_sha256":"582a5d67ba6297f385f06ce7cfa8153ebfaa103e7b908ad5832e60d13f75e838"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:15:36.539067Z","signature_b64":"pRUbDE1qRlIlsobRqLtX0qD42xnr/ObR3YxHlNacY9utjnZa9A9HxuaK4Xvt0qE9PZTdliUctCt1gTqohRGLCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4d902497d0c65d5c320598f4cabbdb8311764bf738f53d278bec2b282d230e7","last_reissued_at":"2026-07-05T02:15:36.538675Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:15:36.538675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jonathan Le Roux, Niko Moritz, Sameer Khurana, Takaaki Hori","submitted_at":"2020-11-26T18:51:26Z","abstract_excerpt":"The performance of automatic speech recognition (ASR) systems typically degrades significantly when the training and test data domains are mismatched. In this paper, we show that self-training (ST) combined with an uncertainty-based pseudo-label filtering approach can be effectively used for domain adaptation. We propose DUST, a dropout-based uncertainty-driven self-training technique which uses agreement between multiple predictions of an ASR system obtained for different dropout settings to measure the model's uncertainty about its prediction. DUST excludes pseudo-labeled data with high unce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.13439","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/2011.13439/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":"2011.13439","created_at":"2026-07-05T02:15:36.538739+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.13439v2","created_at":"2026-07-05T02:15:36.538739+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.13439","created_at":"2026-07-05T02:15:36.538739+00:00"},{"alias_kind":"pith_short_12","alias_value":"6TMQESL5BRS5","created_at":"2026-07-05T02:15:36.538739+00:00"},{"alias_kind":"pith_short_16","alias_value":"6TMQESL5BRS5LQZA","created_at":"2026-07-05T02:15:36.538739+00:00"},{"alias_kind":"pith_short_8","alias_value":"6TMQESL5","created_at":"2026-07-05T02:15:36.538739+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/6TMQESL5BRS5LQZALGHUZK55XA","json":"https://pith.science/pith/6TMQESL5BRS5LQZALGHUZK55XA.json","graph_json":"https://pith.science/api/pith-number/6TMQESL5BRS5LQZALGHUZK55XA/graph.json","events_json":"https://pith.science/api/pith-number/6TMQESL5BRS5LQZALGHUZK55XA/events.json","paper":"https://pith.science/paper/6TMQESL5"},"agent_actions":{"view_html":"https://pith.science/pith/6TMQESL5BRS5LQZALGHUZK55XA","download_json":"https://pith.science/pith/6TMQESL5BRS5LQZALGHUZK55XA.json","view_paper":"https://pith.science/paper/6TMQESL5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.13439&json=true","fetch_graph":"https://pith.science/api/pith-number/6TMQESL5BRS5LQZALGHUZK55XA/graph.json","fetch_events":"https://pith.science/api/pith-number/6TMQESL5BRS5LQZALGHUZK55XA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6TMQESL5BRS5LQZALGHUZK55XA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6TMQESL5BRS5LQZALGHUZK55XA/action/storage_attestation","attest_author":"https://pith.science/pith/6TMQESL5BRS5LQZALGHUZK55XA/action/author_attestation","sign_citation":"https://pith.science/pith/6TMQESL5BRS5LQZALGHUZK55XA/action/citation_signature","submit_replication":"https://pith.science/pith/6TMQESL5BRS5LQZALGHUZK55XA/action/replication_record"}},"created_at":"2026-07-05T02:15:36.538739+00:00","updated_at":"2026-07-05T02:15:36.538739+00:00"}