{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JPT5B2SE2HYKIYWAOMNPH2C2EE","short_pith_number":"pith:JPT5B2SE","schema_version":"1.0","canonical_sha256":"4be7d0ea44d1f0a462c0731af3e85a210ecaf1aa47a18b08ddc93f010bd8c109","source":{"kind":"arxiv","id":"2305.12493","version":5},"attestation_state":"computed","paper":{"title":"Contextualized End-to-End Speech Recognition with Contextual Phrase Prediction Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ao Zhang, Bingshen Mu, Kaixun Huang, Lei Xie, Pengcheng Guo, Tianyi Xu, Zhanheng Yang","submitted_at":"2023-05-21T16:08:04Z","abstract_excerpt":"Contextual information plays a crucial role in speech recognition technologies and incorporating it into the end-to-end speech recognition models has drawn immense interest recently. However, previous deep bias methods lacked explicit supervision for bias tasks. In this study, we introduce a contextual phrase prediction network for an attention-based deep bias method. This network predicts context phrases in utterances using contextual embeddings and calculates bias loss to assist in the training of the contextualized model. Our method achieved a significant word error rate (WER) reduction acr"},"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":"2305.12493","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-05-21T16:08:04Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"e718041e5efa47c65e3f19bd6883b29f4ae3d85b276fe8174a98563c87dcf66b","abstract_canon_sha256":"cf5948028ae120e55c45354c14c9dd43bafcd4b2f8b46260e2321d4d554da018"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:19.337284Z","signature_b64":"IkvDyURxU02uhSvEQfBbIdaF1Onz/qTTL/CL3oSOJOkPZg+au2jqbV2ssSMnaqvRofA548dF61U/+8UgjihrCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4be7d0ea44d1f0a462c0731af3e85a210ecaf1aa47a18b08ddc93f010bd8c109","last_reissued_at":"2026-07-05T06:30:19.336787Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:19.336787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contextualized End-to-End Speech Recognition with Contextual Phrase Prediction Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ao Zhang, Bingshen Mu, Kaixun Huang, Lei Xie, Pengcheng Guo, Tianyi Xu, Zhanheng Yang","submitted_at":"2023-05-21T16:08:04Z","abstract_excerpt":"Contextual information plays a crucial role in speech recognition technologies and incorporating it into the end-to-end speech recognition models has drawn immense interest recently. However, previous deep bias methods lacked explicit supervision for bias tasks. In this study, we introduce a contextual phrase prediction network for an attention-based deep bias method. This network predicts context phrases in utterances using contextual embeddings and calculates bias loss to assist in the training of the contextualized model. Our method achieved a significant word error rate (WER) reduction acr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12493","kind":"arxiv","version":5},"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/2305.12493/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":"2305.12493","created_at":"2026-07-05T06:30:19.336853+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.12493v5","created_at":"2026-07-05T06:30:19.336853+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12493","created_at":"2026-07-05T06:30:19.336853+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPT5B2SE2HYK","created_at":"2026-07-05T06:30:19.336853+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPT5B2SE2HYKIYWA","created_at":"2026-07-05T06:30:19.336853+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPT5B2SE","created_at":"2026-07-05T06:30:19.336853+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08961","citing_title":"Dolphin-CN-Dialect: Where Chinese Dialects Matter","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JPT5B2SE2HYKIYWAOMNPH2C2EE","json":"https://pith.science/pith/JPT5B2SE2HYKIYWAOMNPH2C2EE.json","graph_json":"https://pith.science/api/pith-number/JPT5B2SE2HYKIYWAOMNPH2C2EE/graph.json","events_json":"https://pith.science/api/pith-number/JPT5B2SE2HYKIYWAOMNPH2C2EE/events.json","paper":"https://pith.science/paper/JPT5B2SE"},"agent_actions":{"view_html":"https://pith.science/pith/JPT5B2SE2HYKIYWAOMNPH2C2EE","download_json":"https://pith.science/pith/JPT5B2SE2HYKIYWAOMNPH2C2EE.json","view_paper":"https://pith.science/paper/JPT5B2SE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.12493&json=true","fetch_graph":"https://pith.science/api/pith-number/JPT5B2SE2HYKIYWAOMNPH2C2EE/graph.json","fetch_events":"https://pith.science/api/pith-number/JPT5B2SE2HYKIYWAOMNPH2C2EE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPT5B2SE2HYKIYWAOMNPH2C2EE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPT5B2SE2HYKIYWAOMNPH2C2EE/action/storage_attestation","attest_author":"https://pith.science/pith/JPT5B2SE2HYKIYWAOMNPH2C2EE/action/author_attestation","sign_citation":"https://pith.science/pith/JPT5B2SE2HYKIYWAOMNPH2C2EE/action/citation_signature","submit_replication":"https://pith.science/pith/JPT5B2SE2HYKIYWAOMNPH2C2EE/action/replication_record"}},"created_at":"2026-07-05T06:30:19.336853+00:00","updated_at":"2026-07-05T06:30:19.336853+00:00"}