{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KMZLTSBBYFT7UWOSEYDIHWYJEH","short_pith_number":"pith:KMZLTSBB","schema_version":"1.0","canonical_sha256":"5332b9c821c167fa59d2260683db0921f73ee47dd6b1c3b7aebc35cbe994da7d","source":{"kind":"arxiv","id":"1808.02480","version":1},"attestation_state":"computed","paper":{"title":"Deep context: end-to-end contextual speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Anjuli Kannan, Ding Zhao, Golan Pundak, Rohit Prabhavalkar, Tara N. Sainath","submitted_at":"2018-08-07T21:23:21Z","abstract_excerpt":"In automatic speech recognition (ASR) what a user says depends on the particular context she is in. Typically, this context is represented as a set of word n-grams. In this work, we present a novel, all-neural, end-to-end (E2E) ASR sys- tem that utilizes such context. Our approach, which we re- fer to as Contextual Listen, Attend and Spell (CLAS) jointly- optimizes the ASR components along with embeddings of the context n-grams. During inference, the CLAS system can be presented with context phrases which might contain out-of- vocabulary (OOV) terms not seen during training. We com- pare our p"},"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":"1808.02480","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-08-07T21:23:21Z","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"5831fa263303fa9370eaf39900d9f4a661b2cb773aa467e14559a0c5d4604835","abstract_canon_sha256":"15070367c7429f030f4afa1732c64054b1fc9b638dedc24fbcc2ce4d901b3d2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:35.269455Z","signature_b64":"hw6iX4WoH5fXI6KFDeJ5ElZl4tV8kxgqKSnrQ/ZMyLyUbarrqpNVzcWaT4F17I+N7a8e1saPtup6jlx6azRAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5332b9c821c167fa59d2260683db0921f73ee47dd6b1c3b7aebc35cbe994da7d","last_reissued_at":"2026-05-18T00:08:35.268923Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:35.268923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep context: end-to-end contextual speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Anjuli Kannan, Ding Zhao, Golan Pundak, Rohit Prabhavalkar, Tara N. Sainath","submitted_at":"2018-08-07T21:23:21Z","abstract_excerpt":"In automatic speech recognition (ASR) what a user says depends on the particular context she is in. Typically, this context is represented as a set of word n-grams. In this work, we present a novel, all-neural, end-to-end (E2E) ASR sys- tem that utilizes such context. Our approach, which we re- fer to as Contextual Listen, Attend and Spell (CLAS) jointly- optimizes the ASR components along with embeddings of the context n-grams. During inference, the CLAS system can be presented with context phrases which might contain out-of- vocabulary (OOV) terms not seen during training. We com- pare our p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.02480","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":"1808.02480","created_at":"2026-05-18T00:08:35.269001+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.02480v1","created_at":"2026-05-18T00:08:35.269001+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.02480","created_at":"2026-05-18T00:08:35.269001+00:00"},{"alias_kind":"pith_short_12","alias_value":"KMZLTSBBYFT7","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KMZLTSBBYFT7UWOS","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KMZLTSBB","created_at":"2026-05-18T12:32:33.847187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.09292","citing_title":"Phoneme-Based Contextualization for Cross-Lingual Speech Recognition in End-to-End Models","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"1907.10726","citing_title":"Cross-Attention End-to-End ASR for Two-Party Conversations","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KMZLTSBBYFT7UWOSEYDIHWYJEH","json":"https://pith.science/pith/KMZLTSBBYFT7UWOSEYDIHWYJEH.json","graph_json":"https://pith.science/api/pith-number/KMZLTSBBYFT7UWOSEYDIHWYJEH/graph.json","events_json":"https://pith.science/api/pith-number/KMZLTSBBYFT7UWOSEYDIHWYJEH/events.json","paper":"https://pith.science/paper/KMZLTSBB"},"agent_actions":{"view_html":"https://pith.science/pith/KMZLTSBBYFT7UWOSEYDIHWYJEH","download_json":"https://pith.science/pith/KMZLTSBBYFT7UWOSEYDIHWYJEH.json","view_paper":"https://pith.science/paper/KMZLTSBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.02480&json=true","fetch_graph":"https://pith.science/api/pith-number/KMZLTSBBYFT7UWOSEYDIHWYJEH/graph.json","fetch_events":"https://pith.science/api/pith-number/KMZLTSBBYFT7UWOSEYDIHWYJEH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KMZLTSBBYFT7UWOSEYDIHWYJEH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KMZLTSBBYFT7UWOSEYDIHWYJEH/action/storage_attestation","attest_author":"https://pith.science/pith/KMZLTSBBYFT7UWOSEYDIHWYJEH/action/author_attestation","sign_citation":"https://pith.science/pith/KMZLTSBBYFT7UWOSEYDIHWYJEH/action/citation_signature","submit_replication":"https://pith.science/pith/KMZLTSBBYFT7UWOSEYDIHWYJEH/action/replication_record"}},"created_at":"2026-05-18T00:08:35.269001+00:00","updated_at":"2026-05-18T00:08:35.269001+00:00"}