{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PWEY5PELO7SRPKFPDLNQ2FF7OO","short_pith_number":"pith:PWEY5PEL","schema_version":"1.0","canonical_sha256":"7d898ebc8b77e517a8af1adb0d14bf738275c2b5ccca76346be4be98bb9984ec","source":{"kind":"arxiv","id":"2110.05241","version":1},"attestation_state":"computed","paper":{"title":"Streaming Transformer Transducer Based Speech Recognition Using Non-Causal Convolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"eess.AS","authors_text":"Alex Xiao, Chunxi Liu, Chunyang Wu, Dilin Wang, Jay Mahadeokar, Ke Li, Mike Seltzer, Ozlem Kalinli, Varun Nagaraja, Xiaohui Zhang, Yangyang Shi, Yuan Shangguan","submitted_at":"2021-10-07T21:36:48Z","abstract_excerpt":"This paper improves the streaming transformer transducer for speech recognition by using non-causal convolution. Many works apply the causal convolution to improve streaming transformer ignoring the lookahead context. We propose to use non-causal convolution to process the center block and lookahead context separately. This method leverages the lookahead context in convolution and maintains similar training and decoding efficiency. Given the similar latency, using the non-causal convolution with lookahead context gives better accuracy than causal convolution, especially for open-domain dictati"},"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":"2110.05241","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-10-07T21:36:48Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"93c4b6a176146907ae30f259c97560e83146acae94f564b467160cf48ea835a5","abstract_canon_sha256":"1e6f44809e0f84c1ec696949c13e1056a936b735fe6c3bbdc06c25670393ea33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:21:26.845293Z","signature_b64":"KGDMOICUMfnZpa8cprlBMlD3wdNE6+AYRYYyDkx3huAxX3REIyS//6lzcmneD3/sU+vcSzEQiLg1Mcq57Y08Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d898ebc8b77e517a8af1adb0d14bf738275c2b5ccca76346be4be98bb9984ec","last_reissued_at":"2026-07-05T03:21:26.844949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:21:26.844949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Streaming Transformer Transducer Based Speech Recognition Using Non-Causal Convolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"eess.AS","authors_text":"Alex Xiao, Chunxi Liu, Chunyang Wu, Dilin Wang, Jay Mahadeokar, Ke Li, Mike Seltzer, Ozlem Kalinli, Varun Nagaraja, Xiaohui Zhang, Yangyang Shi, Yuan Shangguan","submitted_at":"2021-10-07T21:36:48Z","abstract_excerpt":"This paper improves the streaming transformer transducer for speech recognition by using non-causal convolution. Many works apply the causal convolution to improve streaming transformer ignoring the lookahead context. We propose to use non-causal convolution to process the center block and lookahead context separately. This method leverages the lookahead context in convolution and maintains similar training and decoding efficiency. Given the similar latency, using the non-causal convolution with lookahead context gives better accuracy than causal convolution, especially for open-domain dictati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05241","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/2110.05241/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":"2110.05241","created_at":"2026-07-05T03:21:26.845004+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.05241v1","created_at":"2026-07-05T03:21:26.845004+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05241","created_at":"2026-07-05T03:21:26.845004+00:00"},{"alias_kind":"pith_short_12","alias_value":"PWEY5PELO7SR","created_at":"2026-07-05T03:21:26.845004+00:00"},{"alias_kind":"pith_short_16","alias_value":"PWEY5PELO7SRPKFP","created_at":"2026-07-05T03:21:26.845004+00:00"},{"alias_kind":"pith_short_8","alias_value":"PWEY5PEL","created_at":"2026-07-05T03:21:26.845004+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/PWEY5PELO7SRPKFPDLNQ2FF7OO","json":"https://pith.science/pith/PWEY5PELO7SRPKFPDLNQ2FF7OO.json","graph_json":"https://pith.science/api/pith-number/PWEY5PELO7SRPKFPDLNQ2FF7OO/graph.json","events_json":"https://pith.science/api/pith-number/PWEY5PELO7SRPKFPDLNQ2FF7OO/events.json","paper":"https://pith.science/paper/PWEY5PEL"},"agent_actions":{"view_html":"https://pith.science/pith/PWEY5PELO7SRPKFPDLNQ2FF7OO","download_json":"https://pith.science/pith/PWEY5PELO7SRPKFPDLNQ2FF7OO.json","view_paper":"https://pith.science/paper/PWEY5PEL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.05241&json=true","fetch_graph":"https://pith.science/api/pith-number/PWEY5PELO7SRPKFPDLNQ2FF7OO/graph.json","fetch_events":"https://pith.science/api/pith-number/PWEY5PELO7SRPKFPDLNQ2FF7OO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PWEY5PELO7SRPKFPDLNQ2FF7OO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PWEY5PELO7SRPKFPDLNQ2FF7OO/action/storage_attestation","attest_author":"https://pith.science/pith/PWEY5PELO7SRPKFPDLNQ2FF7OO/action/author_attestation","sign_citation":"https://pith.science/pith/PWEY5PELO7SRPKFPDLNQ2FF7OO/action/citation_signature","submit_replication":"https://pith.science/pith/PWEY5PELO7SRPKFPDLNQ2FF7OO/action/replication_record"}},"created_at":"2026-07-05T03:21:26.845004+00:00","updated_at":"2026-07-05T03:21:26.845004+00:00"}