{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7AMEDQR4ROOSLRHR4RTOJBHL35","short_pith_number":"pith:7AMEDQR4","schema_version":"1.0","canonical_sha256":"f81841c23c8b9d25c4f1e466e484ebdf4d381dfba0a51a46ab04643ee8bb1319","source":{"kind":"arxiv","id":"1912.00863","version":1},"attestation_state":"computed","paper":{"title":"Independent language modeling architecture for end-to-end ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Bin Ma, Chongjia Ni, Eng Siong Chng, Haihua Xu, Haizhou Li, Van Tung Pham, Yerbolat Khassanov, Zhiping Zeng","submitted_at":"2019-11-25T07:35:16Z","abstract_excerpt":"The attention-based end-to-end (E2E) automatic speech recognition (ASR) architecture allows for joint optimization of acoustic and language models within a single network. However, in a vanilla E2E ASR architecture, the decoder sub-network (subnet), which incorporates the role of the language model (LM), is conditioned on the encoder output. This means that the acoustic encoder and the language model are entangled that doesn't allow language model to be trained separately from external text data. To address this problem, in this work, we propose a new architecture that separates the decoder su"},"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":"1912.00863","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-25T07:35:16Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"f94b1536d9ea138f5a9c752999d8d2447ba8cdfccc886e263fd84d10ed35142b","abstract_canon_sha256":"3bb1d9762a8b8b4ffa0f45e415eed3250ce9fce836e6b62343d668186d4ac8be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:23:17.543076Z","signature_b64":"c3eQUPkwHHUcc3NluaifDQlb4/NoJ0y1OjvU1GScdq77CG6XxCMQH/rWXG6LRzMQT1VaHklZSFXAfwe+W0EwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f81841c23c8b9d25c4f1e466e484ebdf4d381dfba0a51a46ab04643ee8bb1319","last_reissued_at":"2026-07-05T00:23:17.542714Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:23:17.542714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Independent language modeling architecture for end-to-end ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Bin Ma, Chongjia Ni, Eng Siong Chng, Haihua Xu, Haizhou Li, Van Tung Pham, Yerbolat Khassanov, Zhiping Zeng","submitted_at":"2019-11-25T07:35:16Z","abstract_excerpt":"The attention-based end-to-end (E2E) automatic speech recognition (ASR) architecture allows for joint optimization of acoustic and language models within a single network. However, in a vanilla E2E ASR architecture, the decoder sub-network (subnet), which incorporates the role of the language model (LM), is conditioned on the encoder output. This means that the acoustic encoder and the language model are entangled that doesn't allow language model to be trained separately from external text data. To address this problem, in this work, we propose a new architecture that separates the decoder su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.00863","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.00863/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":"1912.00863","created_at":"2026-07-05T00:23:17.542771+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.00863v1","created_at":"2026-07-05T00:23:17.542771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.00863","created_at":"2026-07-05T00:23:17.542771+00:00"},{"alias_kind":"pith_short_12","alias_value":"7AMEDQR4ROOS","created_at":"2026-07-05T00:23:17.542771+00:00"},{"alias_kind":"pith_short_16","alias_value":"7AMEDQR4ROOSLRHR","created_at":"2026-07-05T00:23:17.542771+00:00"},{"alias_kind":"pith_short_8","alias_value":"7AMEDQR4","created_at":"2026-07-05T00:23:17.542771+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/7AMEDQR4ROOSLRHR4RTOJBHL35","json":"https://pith.science/pith/7AMEDQR4ROOSLRHR4RTOJBHL35.json","graph_json":"https://pith.science/api/pith-number/7AMEDQR4ROOSLRHR4RTOJBHL35/graph.json","events_json":"https://pith.science/api/pith-number/7AMEDQR4ROOSLRHR4RTOJBHL35/events.json","paper":"https://pith.science/paper/7AMEDQR4"},"agent_actions":{"view_html":"https://pith.science/pith/7AMEDQR4ROOSLRHR4RTOJBHL35","download_json":"https://pith.science/pith/7AMEDQR4ROOSLRHR4RTOJBHL35.json","view_paper":"https://pith.science/paper/7AMEDQR4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.00863&json=true","fetch_graph":"https://pith.science/api/pith-number/7AMEDQR4ROOSLRHR4RTOJBHL35/graph.json","fetch_events":"https://pith.science/api/pith-number/7AMEDQR4ROOSLRHR4RTOJBHL35/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7AMEDQR4ROOSLRHR4RTOJBHL35/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7AMEDQR4ROOSLRHR4RTOJBHL35/action/storage_attestation","attest_author":"https://pith.science/pith/7AMEDQR4ROOSLRHR4RTOJBHL35/action/author_attestation","sign_citation":"https://pith.science/pith/7AMEDQR4ROOSLRHR4RTOJBHL35/action/citation_signature","submit_replication":"https://pith.science/pith/7AMEDQR4ROOSLRHR4RTOJBHL35/action/replication_record"}},"created_at":"2026-07-05T00:23:17.542771+00:00","updated_at":"2026-07-05T00:23:17.542771+00:00"}