{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GMXZGVNFPHNK3ZHQUGJJK5FW3E","short_pith_number":"pith:GMXZGVNF","schema_version":"1.0","canonical_sha256":"332f9355a579daade4f0a1929574b6d90c598a2d4c2593082fd16b9c66270162","source":{"kind":"arxiv","id":"2210.16238","version":1},"attestation_state":"computed","paper":{"title":"Contextual-Utterance Training for Automatic Speech Recognition","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Alejandro Gomez-Alanis, Andreas Schwarz, Lukas Drude, Rupak Vignesh Swaminathan, Simon Wiesler","submitted_at":"2022-10-27T08:10:44Z","abstract_excerpt":"Recent studies of streaming automatic speech recognition (ASR) recurrent neural network transducer (RNN-T)-based systems have fed the encoder with past contextual information in order to improve its word error rate (WER) performance. In this paper, we first propose a contextual-utterance training technique which makes use of the previous and future contextual utterances in order to do an implicit adaptation to the speaker, topic and acoustic environment. Also, we propose a dual-mode contextual-utterance training technique for streaming automatic speech recognition (ASR) systems. This proposed "},"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":"2210.16238","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.AS","submitted_at":"2022-10-27T08:10:44Z","cross_cats_sorted":["cs.LG","cs.SD","eess.SP"],"title_canon_sha256":"37ef4f5480408ea0c4729689a37665274fcb7ea307df4e2c9e8d020b6c47e9cc","abstract_canon_sha256":"db5dcfbeebb2fdb2173b6ebc669e8d4d15f8df16c82d9f79b68aa8fc9baf4881"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:31.935886Z","signature_b64":"jy+tIPHHowyjyJx7bRlixKS/pML5/BN8awEMFT4IMe+JucEe/Bcz+5k/4P/6+y5xzLkP7XL5CMC1WmE3LT22Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"332f9355a579daade4f0a1929574b6d90c598a2d4c2593082fd16b9c66270162","last_reissued_at":"2026-07-05T05:11:31.935389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:31.935389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contextual-Utterance Training for Automatic Speech Recognition","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Alejandro Gomez-Alanis, Andreas Schwarz, Lukas Drude, Rupak Vignesh Swaminathan, Simon Wiesler","submitted_at":"2022-10-27T08:10:44Z","abstract_excerpt":"Recent studies of streaming automatic speech recognition (ASR) recurrent neural network transducer (RNN-T)-based systems have fed the encoder with past contextual information in order to improve its word error rate (WER) performance. In this paper, we first propose a contextual-utterance training technique which makes use of the previous and future contextual utterances in order to do an implicit adaptation to the speaker, topic and acoustic environment. Also, we propose a dual-mode contextual-utterance training technique for streaming automatic speech recognition (ASR) systems. This proposed "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16238","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/2210.16238/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":"2210.16238","created_at":"2026-07-05T05:11:31.935450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.16238v1","created_at":"2026-07-05T05:11:31.935450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16238","created_at":"2026-07-05T05:11:31.935450+00:00"},{"alias_kind":"pith_short_12","alias_value":"GMXZGVNFPHNK","created_at":"2026-07-05T05:11:31.935450+00:00"},{"alias_kind":"pith_short_16","alias_value":"GMXZGVNFPHNK3ZHQ","created_at":"2026-07-05T05:11:31.935450+00:00"},{"alias_kind":"pith_short_8","alias_value":"GMXZGVNF","created_at":"2026-07-05T05:11:31.935450+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/GMXZGVNFPHNK3ZHQUGJJK5FW3E","json":"https://pith.science/pith/GMXZGVNFPHNK3ZHQUGJJK5FW3E.json","graph_json":"https://pith.science/api/pith-number/GMXZGVNFPHNK3ZHQUGJJK5FW3E/graph.json","events_json":"https://pith.science/api/pith-number/GMXZGVNFPHNK3ZHQUGJJK5FW3E/events.json","paper":"https://pith.science/paper/GMXZGVNF"},"agent_actions":{"view_html":"https://pith.science/pith/GMXZGVNFPHNK3ZHQUGJJK5FW3E","download_json":"https://pith.science/pith/GMXZGVNFPHNK3ZHQUGJJK5FW3E.json","view_paper":"https://pith.science/paper/GMXZGVNF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.16238&json=true","fetch_graph":"https://pith.science/api/pith-number/GMXZGVNFPHNK3ZHQUGJJK5FW3E/graph.json","fetch_events":"https://pith.science/api/pith-number/GMXZGVNFPHNK3ZHQUGJJK5FW3E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GMXZGVNFPHNK3ZHQUGJJK5FW3E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GMXZGVNFPHNK3ZHQUGJJK5FW3E/action/storage_attestation","attest_author":"https://pith.science/pith/GMXZGVNFPHNK3ZHQUGJJK5FW3E/action/author_attestation","sign_citation":"https://pith.science/pith/GMXZGVNFPHNK3ZHQUGJJK5FW3E/action/citation_signature","submit_replication":"https://pith.science/pith/GMXZGVNFPHNK3ZHQUGJJK5FW3E/action/replication_record"}},"created_at":"2026-07-05T05:11:31.935450+00:00","updated_at":"2026-07-05T05:11:31.935450+00:00"}