{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:AV5566HTQLTKFFSOM5DXMHG2XL","short_pith_number":"pith:AV5566HT","schema_version":"1.0","canonical_sha256":"057bdf78f382e6a2964e6747761cdabad2d53a459c6397871e017e435decf837","source":{"kind":"arxiv","id":"1708.05466","version":1},"attestation_state":"computed","paper":{"title":"Large-Scale Domain Adaptation via Teacher-Student Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jinyu Li, Michael L. Seltzer, Rui Zhao, Xi Wang, Yifan Gong","submitted_at":"2017-08-17T23:37:18Z","abstract_excerpt":"High accuracy speech recognition requires a large amount of transcribed data for supervised training. In the absence of such data, domain adaptation of a well-trained acoustic model can be performed, but even here, high accuracy usually requires significant labeled data from the target domain. In this work, we propose an approach to domain adaptation that does not require transcriptions but instead uses a corpus of unlabeled parallel data, consisting of pairs of samples from the source domain of the well-trained model and the desired target domain. To perform adaptation, we employ teacher/stud"},"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":"1708.05466","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-17T23:37:18Z","cross_cats_sorted":[],"title_canon_sha256":"509112fe552d8d2514f731630e2d553e148622ed22fc73277519cd9183e2bd54","abstract_canon_sha256":"233fc52a34bc9713e459d96845ebd78353afd11255272b30c8055ad3357d09c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:37:49.979198Z","signature_b64":"P4cz7m7r0qnXiPBGf92cFHEs+Xnemj62Tj390xcdVq+oC7ZhATOrWLcUhciw/nqRhXGz5UlKd0kNatQJ3E7IAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"057bdf78f382e6a2964e6747761cdabad2d53a459c6397871e017e435decf837","last_reissued_at":"2026-05-18T00:37:49.978574Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:37:49.978574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large-Scale Domain Adaptation via Teacher-Student Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jinyu Li, Michael L. Seltzer, Rui Zhao, Xi Wang, Yifan Gong","submitted_at":"2017-08-17T23:37:18Z","abstract_excerpt":"High accuracy speech recognition requires a large amount of transcribed data for supervised training. In the absence of such data, domain adaptation of a well-trained acoustic model can be performed, but even here, high accuracy usually requires significant labeled data from the target domain. In this work, we propose an approach to domain adaptation that does not require transcriptions but instead uses a corpus of unlabeled parallel data, consisting of pairs of samples from the source domain of the well-trained model and the desired target domain. To perform adaptation, we employ teacher/stud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.05466","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":""},"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":"1708.05466","created_at":"2026-05-18T00:37:49.978663+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.05466v1","created_at":"2026-05-18T00:37:49.978663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.05466","created_at":"2026-05-18T00:37:49.978663+00:00"},{"alias_kind":"pith_short_12","alias_value":"AV5566HTQLTK","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"AV5566HTQLTKFFSO","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"AV5566HT","created_at":"2026-05-18T12:31:08.081275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.06017","citing_title":"Learn Spelling from Teachers: Transferring Knowledge from Language Models to Sequence-to-Sequence Speech Recognition","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11256","citing_title":"Teaching the Teachers: Boosting unsupervised domain adaptation in speech recognition by ensemble update","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AV5566HTQLTKFFSOM5DXMHG2XL","json":"https://pith.science/pith/AV5566HTQLTKFFSOM5DXMHG2XL.json","graph_json":"https://pith.science/api/pith-number/AV5566HTQLTKFFSOM5DXMHG2XL/graph.json","events_json":"https://pith.science/api/pith-number/AV5566HTQLTKFFSOM5DXMHG2XL/events.json","paper":"https://pith.science/paper/AV5566HT"},"agent_actions":{"view_html":"https://pith.science/pith/AV5566HTQLTKFFSOM5DXMHG2XL","download_json":"https://pith.science/pith/AV5566HTQLTKFFSOM5DXMHG2XL.json","view_paper":"https://pith.science/paper/AV5566HT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.05466&json=true","fetch_graph":"https://pith.science/api/pith-number/AV5566HTQLTKFFSOM5DXMHG2XL/graph.json","fetch_events":"https://pith.science/api/pith-number/AV5566HTQLTKFFSOM5DXMHG2XL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AV5566HTQLTKFFSOM5DXMHG2XL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AV5566HTQLTKFFSOM5DXMHG2XL/action/storage_attestation","attest_author":"https://pith.science/pith/AV5566HTQLTKFFSOM5DXMHG2XL/action/author_attestation","sign_citation":"https://pith.science/pith/AV5566HTQLTKFFSOM5DXMHG2XL/action/citation_signature","submit_replication":"https://pith.science/pith/AV5566HTQLTKFFSOM5DXMHG2XL/action/replication_record"}},"created_at":"2026-05-18T00:37:49.978663+00:00","updated_at":"2026-05-18T00:37:49.978663+00:00"}