{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5QP3ZGDDJYBCIGJHSBR6N5CEJ5","short_pith_number":"pith:5QP3ZGDD","schema_version":"1.0","canonical_sha256":"ec1fbc98634e022419279063e6f4444f5be49e42fadbed075df1e07e446e2175","source":{"kind":"arxiv","id":"2005.08742","version":1},"attestation_state":"computed","paper":{"title":"Approaches to Improving Recognition of Underrepresented Named Entities in Hybrid ASR Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Eng Siong Chng, Haihua Xu, Hao Huang, Tingzhi Mao, Van Tung Pham, Yerbolat Khassanov","submitted_at":"2020-05-18T14:11:20Z","abstract_excerpt":"In this paper, we present a series of complementary approaches to improve the recognition of underrepresented named entities (NE) in hybrid ASR systems without compromising overall word error rate performance. The underrepresented words correspond to rare or out-of-vocabulary (OOV) words in the training data, and thereby can't be modeled reliably. We begin with graphemic lexicon which allows to drop the necessity of phonetic models in hybrid ASR. We study it under different settings and demonstrate its effectiveness in dealing with underrepresented NEs. Next, we study the impact of neural lang"},"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":"2005.08742","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-18T14:11:20Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"54cfa737e0bb97709ec59d570f499427c22d5ebff00d7b6f19d0fcb3025c6bcf","abstract_canon_sha256":"49d36063506a29f60ad9156531d5f2261ed4f38ced5994c118903de580f796a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:03:35.016405Z","signature_b64":"Wtv5a5e+5t1+lRgu7CoQCPIR5eMck8sQO5FY5yZlzzTmkZ4pDlzw4l30pkruFxipkSJ8ouTYPNrcm59kjojbDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec1fbc98634e022419279063e6f4444f5be49e42fadbed075df1e07e446e2175","last_reissued_at":"2026-07-05T01:03:35.015956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:03:35.015956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Approaches to Improving Recognition of Underrepresented Named Entities in Hybrid ASR Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Eng Siong Chng, Haihua Xu, Hao Huang, Tingzhi Mao, Van Tung Pham, Yerbolat Khassanov","submitted_at":"2020-05-18T14:11:20Z","abstract_excerpt":"In this paper, we present a series of complementary approaches to improve the recognition of underrepresented named entities (NE) in hybrid ASR systems without compromising overall word error rate performance. The underrepresented words correspond to rare or out-of-vocabulary (OOV) words in the training data, and thereby can't be modeled reliably. We begin with graphemic lexicon which allows to drop the necessity of phonetic models in hybrid ASR. We study it under different settings and demonstrate its effectiveness in dealing with underrepresented NEs. Next, we study the impact of neural lang"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.08742","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/2005.08742/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":"2005.08742","created_at":"2026-07-05T01:03:35.016029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.08742v1","created_at":"2026-07-05T01:03:35.016029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.08742","created_at":"2026-07-05T01:03:35.016029+00:00"},{"alias_kind":"pith_short_12","alias_value":"5QP3ZGDDJYBC","created_at":"2026-07-05T01:03:35.016029+00:00"},{"alias_kind":"pith_short_16","alias_value":"5QP3ZGDDJYBCIGJH","created_at":"2026-07-05T01:03:35.016029+00:00"},{"alias_kind":"pith_short_8","alias_value":"5QP3ZGDD","created_at":"2026-07-05T01:03:35.016029+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/5QP3ZGDDJYBCIGJHSBR6N5CEJ5","json":"https://pith.science/pith/5QP3ZGDDJYBCIGJHSBR6N5CEJ5.json","graph_json":"https://pith.science/api/pith-number/5QP3ZGDDJYBCIGJHSBR6N5CEJ5/graph.json","events_json":"https://pith.science/api/pith-number/5QP3ZGDDJYBCIGJHSBR6N5CEJ5/events.json","paper":"https://pith.science/paper/5QP3ZGDD"},"agent_actions":{"view_html":"https://pith.science/pith/5QP3ZGDDJYBCIGJHSBR6N5CEJ5","download_json":"https://pith.science/pith/5QP3ZGDDJYBCIGJHSBR6N5CEJ5.json","view_paper":"https://pith.science/paper/5QP3ZGDD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.08742&json=true","fetch_graph":"https://pith.science/api/pith-number/5QP3ZGDDJYBCIGJHSBR6N5CEJ5/graph.json","fetch_events":"https://pith.science/api/pith-number/5QP3ZGDDJYBCIGJHSBR6N5CEJ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5QP3ZGDDJYBCIGJHSBR6N5CEJ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5QP3ZGDDJYBCIGJHSBR6N5CEJ5/action/storage_attestation","attest_author":"https://pith.science/pith/5QP3ZGDDJYBCIGJHSBR6N5CEJ5/action/author_attestation","sign_citation":"https://pith.science/pith/5QP3ZGDDJYBCIGJHSBR6N5CEJ5/action/citation_signature","submit_replication":"https://pith.science/pith/5QP3ZGDDJYBCIGJHSBR6N5CEJ5/action/replication_record"}},"created_at":"2026-07-05T01:03:35.016029+00:00","updated_at":"2026-07-05T01:03:35.016029+00:00"}