{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ZKI3M4LTUPHXKMXMB64BML63MQ","short_pith_number":"pith:ZKI3M4LT","schema_version":"1.0","canonical_sha256":"ca91b67173a3cf7532ec0fb8162fdb643a17c8975ec9529c0e8b46ae4db64505","source":{"kind":"arxiv","id":"1711.05448","version":1},"attestation_state":"computed","paper":{"title":"Lattice Rescoring Strategies for Long Short Term Memory Language Models in Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Ananda Theertha Suresh, Daniel Holtmann-Rice, Felix Yu, Hank Liao, Michael Nirschl, Shankar Kumar","submitted_at":"2017-11-15T08:30:56Z","abstract_excerpt":"Recurrent neural network (RNN) language models (LMs) and Long Short Term Memory (LSTM) LMs, a variant of RNN LMs, have been shown to outperform traditional N-gram LMs on speech recognition tasks. However, these models are computationally more expensive than N-gram LMs for decoding, and thus, challenging to integrate into speech recognizers. Recent research has proposed the use of lattice-rescoring algorithms using RNNLMs and LSTMLMs as an efficient strategy to integrate these models into a speech recognition system. In this paper, we evaluate existing lattice rescoring algorithms along with ne"},"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":"1711.05448","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-15T08:30:56Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"fbc6d3daad6b6acd9d5fc1c04ba0c16e64d069107bfde63c8cce8a7cc5d4a3d9","abstract_canon_sha256":"ab5cfda41b71dfcc3413a264a822f138f414131b54380e683d9251e38bd40006"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:29.779594Z","signature_b64":"P9Wt6C4vXq/b8Vq/XF0S7tj2tXCfM1zpaTETn+Trd6pJa6b3fvFxIJa9fXIDO/NX07lDOdlA4iLDiYmvSNgRCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca91b67173a3cf7532ec0fb8162fdb643a17c8975ec9529c0e8b46ae4db64505","last_reissued_at":"2026-05-18T00:30:29.779034Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:29.779034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lattice Rescoring Strategies for Long Short Term Memory Language Models in Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Ananda Theertha Suresh, Daniel Holtmann-Rice, Felix Yu, Hank Liao, Michael Nirschl, Shankar Kumar","submitted_at":"2017-11-15T08:30:56Z","abstract_excerpt":"Recurrent neural network (RNN) language models (LMs) and Long Short Term Memory (LSTM) LMs, a variant of RNN LMs, have been shown to outperform traditional N-gram LMs on speech recognition tasks. However, these models are computationally more expensive than N-gram LMs for decoding, and thus, challenging to integrate into speech recognizers. Recent research has proposed the use of lattice-rescoring algorithms using RNNLMs and LSTMLMs as an efficient strategy to integrate these models into a speech recognition system. In this paper, we evaluate existing lattice rescoring algorithms along with ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.05448","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":"1711.05448","created_at":"2026-05-18T00:30:29.779125+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.05448v1","created_at":"2026-05-18T00:30:29.779125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.05448","created_at":"2026-05-18T00:30:29.779125+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKI3M4LTUPHX","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKI3M4LTUPHXKMXM","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKI3M4LT","created_at":"2026-05-18T12:31:59.375834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.07285","citing_title":"Non-Intrusive Automatic Speech Recognition Refinement: A Survey","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZKI3M4LTUPHXKMXMB64BML63MQ","json":"https://pith.science/pith/ZKI3M4LTUPHXKMXMB64BML63MQ.json","graph_json":"https://pith.science/api/pith-number/ZKI3M4LTUPHXKMXMB64BML63MQ/graph.json","events_json":"https://pith.science/api/pith-number/ZKI3M4LTUPHXKMXMB64BML63MQ/events.json","paper":"https://pith.science/paper/ZKI3M4LT"},"agent_actions":{"view_html":"https://pith.science/pith/ZKI3M4LTUPHXKMXMB64BML63MQ","download_json":"https://pith.science/pith/ZKI3M4LTUPHXKMXMB64BML63MQ.json","view_paper":"https://pith.science/paper/ZKI3M4LT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.05448&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKI3M4LTUPHXKMXMB64BML63MQ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKI3M4LTUPHXKMXMB64BML63MQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKI3M4LTUPHXKMXMB64BML63MQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKI3M4LTUPHXKMXMB64BML63MQ/action/storage_attestation","attest_author":"https://pith.science/pith/ZKI3M4LTUPHXKMXMB64BML63MQ/action/author_attestation","sign_citation":"https://pith.science/pith/ZKI3M4LTUPHXKMXMB64BML63MQ/action/citation_signature","submit_replication":"https://pith.science/pith/ZKI3M4LTUPHXKMXMB64BML63MQ/action/replication_record"}},"created_at":"2026-05-18T00:30:29.779125+00:00","updated_at":"2026-05-18T00:30:29.779125+00:00"}