{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RCH2OQ7YKENGC3SHWWHYGSMOJV","short_pith_number":"pith:RCH2OQ7Y","schema_version":"1.0","canonical_sha256":"888fa743f8511a616e47b58f83498e4d77c72500da3fbce35bc7be0f94bfa9a1","source":{"kind":"arxiv","id":"2211.00792","version":2},"attestation_state":"computed","paper":{"title":"BECTRA: Transducer-based End-to-End ASR with BERT-Enhanced Encoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Shinji Watanabe, Tetsuji Ogawa, Tetsunori Kobayashi, Yosuke Higuchi","submitted_at":"2022-11-02T00:10:43Z","abstract_excerpt":"We present BERT-CTC-Transducer (BECTRA), a novel end-to-end automatic speech recognition (E2E-ASR) model formulated by the transducer with a BERT-enhanced encoder. Integrating a large-scale pre-trained language model (LM) into E2E-ASR has been actively studied, aiming to utilize versatile linguistic knowledge for generating accurate text. One crucial factor that makes this integration challenging lies in the vocabulary mismatch; the vocabulary constructed for a pre-trained LM is generally too large for E2E-ASR training and is likely to have a mismatch against a target ASR domain. To overcome s"},"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":"2211.00792","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-02T00:10:43Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"0a44b567aadc8f63d24fba10da6fc3846719a2bedf10734f3e56da8c27a10483","abstract_canon_sha256":"aad64eb42193a51ded7b7408501bfadb6643b15471920eeb78898180c3a7da34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:56.653603Z","signature_b64":"6bSxLcy4aeEc25bgMNt/iOxbuc1nvJhkndU9o+JihGdUI3fyNGOH5nSILUCkiSfuQ9wJmKQUMIivjqkDlD34Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"888fa743f8511a616e47b58f83498e4d77c72500da3fbce35bc7be0f94bfa9a1","last_reissued_at":"2026-07-05T05:51:56.653030Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:56.653030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BECTRA: Transducer-based End-to-End ASR with BERT-Enhanced Encoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Shinji Watanabe, Tetsuji Ogawa, Tetsunori Kobayashi, Yosuke Higuchi","submitted_at":"2022-11-02T00:10:43Z","abstract_excerpt":"We present BERT-CTC-Transducer (BECTRA), a novel end-to-end automatic speech recognition (E2E-ASR) model formulated by the transducer with a BERT-enhanced encoder. Integrating a large-scale pre-trained language model (LM) into E2E-ASR has been actively studied, aiming to utilize versatile linguistic knowledge for generating accurate text. One crucial factor that makes this integration challenging lies in the vocabulary mismatch; the vocabulary constructed for a pre-trained LM is generally too large for E2E-ASR training and is likely to have a mismatch against a target ASR domain. To overcome s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.00792","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/2211.00792/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":"2211.00792","created_at":"2026-07-05T05:51:56.653094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.00792v2","created_at":"2026-07-05T05:51:56.653094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.00792","created_at":"2026-07-05T05:51:56.653094+00:00"},{"alias_kind":"pith_short_12","alias_value":"RCH2OQ7YKENG","created_at":"2026-07-05T05:51:56.653094+00:00"},{"alias_kind":"pith_short_16","alias_value":"RCH2OQ7YKENGC3SH","created_at":"2026-07-05T05:51:56.653094+00:00"},{"alias_kind":"pith_short_8","alias_value":"RCH2OQ7Y","created_at":"2026-07-05T05:51:56.653094+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/RCH2OQ7YKENGC3SHWWHYGSMOJV","json":"https://pith.science/pith/RCH2OQ7YKENGC3SHWWHYGSMOJV.json","graph_json":"https://pith.science/api/pith-number/RCH2OQ7YKENGC3SHWWHYGSMOJV/graph.json","events_json":"https://pith.science/api/pith-number/RCH2OQ7YKENGC3SHWWHYGSMOJV/events.json","paper":"https://pith.science/paper/RCH2OQ7Y"},"agent_actions":{"view_html":"https://pith.science/pith/RCH2OQ7YKENGC3SHWWHYGSMOJV","download_json":"https://pith.science/pith/RCH2OQ7YKENGC3SHWWHYGSMOJV.json","view_paper":"https://pith.science/paper/RCH2OQ7Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.00792&json=true","fetch_graph":"https://pith.science/api/pith-number/RCH2OQ7YKENGC3SHWWHYGSMOJV/graph.json","fetch_events":"https://pith.science/api/pith-number/RCH2OQ7YKENGC3SHWWHYGSMOJV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RCH2OQ7YKENGC3SHWWHYGSMOJV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RCH2OQ7YKENGC3SHWWHYGSMOJV/action/storage_attestation","attest_author":"https://pith.science/pith/RCH2OQ7YKENGC3SHWWHYGSMOJV/action/author_attestation","sign_citation":"https://pith.science/pith/RCH2OQ7YKENGC3SHWWHYGSMOJV/action/citation_signature","submit_replication":"https://pith.science/pith/RCH2OQ7YKENGC3SHWWHYGSMOJV/action/replication_record"}},"created_at":"2026-07-05T05:51:56.653094+00:00","updated_at":"2026-07-05T05:51:56.653094+00:00"}