{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WCE57WVM5AVYGHMZB7XRIID5Q3","short_pith_number":"pith:WCE57WVM","schema_version":"1.0","canonical_sha256":"b089dfdaace82b831d990fef14207d86fc595222a4ab3df4692a2cfc3ef4ad63","source":{"kind":"arxiv","id":"1907.01677","version":1},"attestation_state":"computed","paper":{"title":"Scalable Multi Corpora Neural Language Models for ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anirudh Raju, Ariya Rastrow, Denis Filimonov, Gautam Tiwari, Guitang Lan","submitted_at":"2019-07-02T23:28:52Z","abstract_excerpt":"Neural language models (NLM) have been shown to outperform conventional n-gram language models by a substantial margin in Automatic Speech Recognition (ASR) and other tasks. There are, however, a number of challenges that need to be addressed for an NLM to be used in a practical large-scale ASR system. In this paper, we present solutions to some of the challenges, including training NLM from heterogenous corpora, limiting latency impact and handling personalized bias in the second-pass rescorer. Overall, we show that we can achieve a 6.2% relative WER reduction using neural LM in a second-pass"},"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":"1907.01677","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-02T23:28:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b6f04fac20f1f7442cd9f7f2c8c2f5d0a43f105cd0e59c606cf937c556e2172b","abstract_canon_sha256":"7793d9a6bc896f0a29b056d333512391c119f4f3a323be21749e8eca724f80c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:35.521649Z","signature_b64":"QJJIYg6c3nAG0Yxt6tOD2lyskwkchkUH1mJ4NbW1tE0SuubOfeu2daaOGuZLMICtRSP3UIhs9+As4bJ8Naz4AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b089dfdaace82b831d990fef14207d86fc595222a4ab3df4692a2cfc3ef4ad63","last_reissued_at":"2026-05-17T23:41:35.521051Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:35.521051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Multi Corpora Neural Language Models for ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anirudh Raju, Ariya Rastrow, Denis Filimonov, Gautam Tiwari, Guitang Lan","submitted_at":"2019-07-02T23:28:52Z","abstract_excerpt":"Neural language models (NLM) have been shown to outperform conventional n-gram language models by a substantial margin in Automatic Speech Recognition (ASR) and other tasks. There are, however, a number of challenges that need to be addressed for an NLM to be used in a practical large-scale ASR system. In this paper, we present solutions to some of the challenges, including training NLM from heterogenous corpora, limiting latency impact and handling personalized bias in the second-pass rescorer. Overall, we show that we can achieve a 6.2% relative WER reduction using neural LM in a second-pass"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.01677","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":"1907.01677","created_at":"2026-05-17T23:41:35.521129+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.01677v1","created_at":"2026-05-17T23:41:35.521129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.01677","created_at":"2026-05-17T23:41:35.521129+00:00"},{"alias_kind":"pith_short_12","alias_value":"WCE57WVM5AVY","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"WCE57WVM5AVYGHMZ","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"WCE57WVM","created_at":"2026-05-18T12:33:30.264802+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/WCE57WVM5AVYGHMZB7XRIID5Q3","json":"https://pith.science/pith/WCE57WVM5AVYGHMZB7XRIID5Q3.json","graph_json":"https://pith.science/api/pith-number/WCE57WVM5AVYGHMZB7XRIID5Q3/graph.json","events_json":"https://pith.science/api/pith-number/WCE57WVM5AVYGHMZB7XRIID5Q3/events.json","paper":"https://pith.science/paper/WCE57WVM"},"agent_actions":{"view_html":"https://pith.science/pith/WCE57WVM5AVYGHMZB7XRIID5Q3","download_json":"https://pith.science/pith/WCE57WVM5AVYGHMZB7XRIID5Q3.json","view_paper":"https://pith.science/paper/WCE57WVM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.01677&json=true","fetch_graph":"https://pith.science/api/pith-number/WCE57WVM5AVYGHMZB7XRIID5Q3/graph.json","fetch_events":"https://pith.science/api/pith-number/WCE57WVM5AVYGHMZB7XRIID5Q3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WCE57WVM5AVYGHMZB7XRIID5Q3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WCE57WVM5AVYGHMZB7XRIID5Q3/action/storage_attestation","attest_author":"https://pith.science/pith/WCE57WVM5AVYGHMZB7XRIID5Q3/action/author_attestation","sign_citation":"https://pith.science/pith/WCE57WVM5AVYGHMZB7XRIID5Q3/action/citation_signature","submit_replication":"https://pith.science/pith/WCE57WVM5AVYGHMZB7XRIID5Q3/action/replication_record"}},"created_at":"2026-05-17T23:41:35.521129+00:00","updated_at":"2026-05-17T23:41:35.521129+00:00"}