{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:4U3Z52JGO4EZPVRH6WPBEVYW5M","short_pith_number":"pith:4U3Z52JG","schema_version":"1.0","canonical_sha256":"e5379ee926770997d627f59e125716eb2663cdb21624c219076145c1f7f461b1","source":{"kind":"arxiv","id":"1808.02608","version":1},"attestation_state":"computed","paper":{"title":"End-to-end Speech Recognition with Word-based RNN Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jaejin Cho, Shinji Watanabe, Takaaki Hori","submitted_at":"2018-08-08T03:05:11Z","abstract_excerpt":"This paper investigates the impact of word-based RNN language models (RNN-LMs) on the performance of end-to-end automatic speech recognition (ASR). In our prior work, we have proposed a multi-level LM, in which character-based and word-based RNN-LMs are combined in hybrid CTC/attention-based ASR. Although this multi-level approach achieves significant error reduction in the Wall Street Journal (WSJ) task, two different LMs need to be trained and used for decoding, which increase the computational cost and memory usage. In this paper, we further propose a novel word-based RNN-LM, which allows u"},"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":"1808.02608","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-08T03:05:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0b0da039e8631b0a865326ea8b919f2880b3ecbacf0cdff2a9934ac3e08561c8","abstract_canon_sha256":"b40957e2ed8accfd8a4487bf207f95e5a4c20fa5b08cebee3b450f2af7d4782a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:34.853700Z","signature_b64":"WqCOQEr5oYsTRg5FofwcNV+XWnJFVM1ElDqa20upebjJ2+JDtMlZV9w22IZqc129EGb+FSMP5olah2aPM531AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5379ee926770997d627f59e125716eb2663cdb21624c219076145c1f7f461b1","last_reissued_at":"2026-05-18T00:08:34.853061Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:34.853061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-end Speech Recognition with Word-based RNN Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jaejin Cho, Shinji Watanabe, Takaaki Hori","submitted_at":"2018-08-08T03:05:11Z","abstract_excerpt":"This paper investigates the impact of word-based RNN language models (RNN-LMs) on the performance of end-to-end automatic speech recognition (ASR). In our prior work, we have proposed a multi-level LM, in which character-based and word-based RNN-LMs are combined in hybrid CTC/attention-based ASR. Although this multi-level approach achieves significant error reduction in the Wall Street Journal (WSJ) task, two different LMs need to be trained and used for decoding, which increase the computational cost and memory usage. In this paper, we further propose a novel word-based RNN-LM, which allows u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.02608","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":"1808.02608","created_at":"2026-05-18T00:08:34.853157+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.02608v1","created_at":"2026-05-18T00:08:34.853157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.02608","created_at":"2026-05-18T00:08:34.853157+00:00"},{"alias_kind":"pith_short_12","alias_value":"4U3Z52JGO4EZ","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"4U3Z52JGO4EZPVRH","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"4U3Z52JG","created_at":"2026-05-18T12:32:05.422762+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/4U3Z52JGO4EZPVRH6WPBEVYW5M","json":"https://pith.science/pith/4U3Z52JGO4EZPVRH6WPBEVYW5M.json","graph_json":"https://pith.science/api/pith-number/4U3Z52JGO4EZPVRH6WPBEVYW5M/graph.json","events_json":"https://pith.science/api/pith-number/4U3Z52JGO4EZPVRH6WPBEVYW5M/events.json","paper":"https://pith.science/paper/4U3Z52JG"},"agent_actions":{"view_html":"https://pith.science/pith/4U3Z52JGO4EZPVRH6WPBEVYW5M","download_json":"https://pith.science/pith/4U3Z52JGO4EZPVRH6WPBEVYW5M.json","view_paper":"https://pith.science/paper/4U3Z52JG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.02608&json=true","fetch_graph":"https://pith.science/api/pith-number/4U3Z52JGO4EZPVRH6WPBEVYW5M/graph.json","fetch_events":"https://pith.science/api/pith-number/4U3Z52JGO4EZPVRH6WPBEVYW5M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4U3Z52JGO4EZPVRH6WPBEVYW5M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4U3Z52JGO4EZPVRH6WPBEVYW5M/action/storage_attestation","attest_author":"https://pith.science/pith/4U3Z52JGO4EZPVRH6WPBEVYW5M/action/author_attestation","sign_citation":"https://pith.science/pith/4U3Z52JGO4EZPVRH6WPBEVYW5M/action/citation_signature","submit_replication":"https://pith.science/pith/4U3Z52JGO4EZPVRH6WPBEVYW5M/action/replication_record"}},"created_at":"2026-05-18T00:08:34.853157+00:00","updated_at":"2026-05-18T00:08:34.853157+00:00"}