{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JON3LGPCBTO4HYGHZPVVQIWIN5","short_pith_number":"pith:JON3LGPC","schema_version":"1.0","canonical_sha256":"4b9bb599e20cddc3e0c7cbeb5822c86f70c36076cfb1fa64507b4bf9c42ad4ff","source":{"kind":"arxiv","id":"2201.11867","version":2},"attestation_state":"computed","paper":{"title":"Neural-FST Class Language Model for End-to-End Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Antoine Bruguier, Bo Wang, Dangna Li, Duc Le, Eun Chang, Fuchun Peng, Michael L. Seltzer, Ozlem Kalinli, Rohit Prabhavalkar, Zhe Liu","submitted_at":"2022-01-28T00:20:57Z","abstract_excerpt":"We propose Neural-FST Class Language Model (NFCLM) for end-to-end speech recognition, a novel method that combines neural network language models (NNLMs) and finite state transducers (FSTs) in a mathematically consistent framework. Our method utilizes a background NNLM which models generic background text together with a collection of domain-specific entities modeled as individual FSTs. Each output token is generated by a mixture of these components; the mixture weights are estimated with a separately trained neural decider. We show that NFCLM significantly outperforms NNLM by 15.8% relative i"},"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":"2201.11867","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-28T00:20:57Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"b7a3dd429e3877ea861aa6019ec6d4b81da65560e1427068435a754012d83fae","abstract_canon_sha256":"4917112a054eeda2dd77a358e284eefb9c7de80170ad615492c363a94b0d2ec4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:52:50.201309Z","signature_b64":"quL8++2hWJEgAMHr0mctfmPJmxTdyLu/Ba8pznjco6fdUYs+GLhnLdOVehIx0wi7V0kwERpmklRSPz3LeiF0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b9bb599e20cddc3e0c7cbeb5822c86f70c36076cfb1fa64507b4bf9c42ad4ff","last_reissued_at":"2026-07-05T03:52:50.200854Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:52:50.200854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural-FST Class Language Model for End-to-End Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Antoine Bruguier, Bo Wang, Dangna Li, Duc Le, Eun Chang, Fuchun Peng, Michael L. Seltzer, Ozlem Kalinli, Rohit Prabhavalkar, Zhe Liu","submitted_at":"2022-01-28T00:20:57Z","abstract_excerpt":"We propose Neural-FST Class Language Model (NFCLM) for end-to-end speech recognition, a novel method that combines neural network language models (NNLMs) and finite state transducers (FSTs) in a mathematically consistent framework. Our method utilizes a background NNLM which models generic background text together with a collection of domain-specific entities modeled as individual FSTs. Each output token is generated by a mixture of these components; the mixture weights are estimated with a separately trained neural decider. We show that NFCLM significantly outperforms NNLM by 15.8% relative i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.11867","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/2201.11867/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":"2201.11867","created_at":"2026-07-05T03:52:50.200911+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.11867v2","created_at":"2026-07-05T03:52:50.200911+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.11867","created_at":"2026-07-05T03:52:50.200911+00:00"},{"alias_kind":"pith_short_12","alias_value":"JON3LGPCBTO4","created_at":"2026-07-05T03:52:50.200911+00:00"},{"alias_kind":"pith_short_16","alias_value":"JON3LGPCBTO4HYGH","created_at":"2026-07-05T03:52:50.200911+00:00"},{"alias_kind":"pith_short_8","alias_value":"JON3LGPC","created_at":"2026-07-05T03:52:50.200911+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/JON3LGPCBTO4HYGHZPVVQIWIN5","json":"https://pith.science/pith/JON3LGPCBTO4HYGHZPVVQIWIN5.json","graph_json":"https://pith.science/api/pith-number/JON3LGPCBTO4HYGHZPVVQIWIN5/graph.json","events_json":"https://pith.science/api/pith-number/JON3LGPCBTO4HYGHZPVVQIWIN5/events.json","paper":"https://pith.science/paper/JON3LGPC"},"agent_actions":{"view_html":"https://pith.science/pith/JON3LGPCBTO4HYGHZPVVQIWIN5","download_json":"https://pith.science/pith/JON3LGPCBTO4HYGHZPVVQIWIN5.json","view_paper":"https://pith.science/paper/JON3LGPC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.11867&json=true","fetch_graph":"https://pith.science/api/pith-number/JON3LGPCBTO4HYGHZPVVQIWIN5/graph.json","fetch_events":"https://pith.science/api/pith-number/JON3LGPCBTO4HYGHZPVVQIWIN5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JON3LGPCBTO4HYGHZPVVQIWIN5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JON3LGPCBTO4HYGHZPVVQIWIN5/action/storage_attestation","attest_author":"https://pith.science/pith/JON3LGPCBTO4HYGHZPVVQIWIN5/action/author_attestation","sign_citation":"https://pith.science/pith/JON3LGPCBTO4HYGHZPVVQIWIN5/action/citation_signature","submit_replication":"https://pith.science/pith/JON3LGPCBTO4HYGHZPVVQIWIN5/action/replication_record"}},"created_at":"2026-07-05T03:52:50.200911+00:00","updated_at":"2026-07-05T03:52:50.200911+00:00"}