{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UUYVYYKP66Q2WYVDHWM2ZA2SJL","short_pith_number":"pith:UUYVYYKP","schema_version":"1.0","canonical_sha256":"a5315c614ff7a1ab62a33d99ac83524ae8cbec8db7b736b9c023b67c1d204855","source":{"kind":"arxiv","id":"2211.00490","version":1},"attestation_state":"computed","paper":{"title":"Delay-penalized transducer for low-latency streaming ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Daniel Povey, Fangjun Kuang, Liyong Guo, Long Lin, Piotr \\.Zelasko, Wei Kang, Xiaoyu Yang, Zengwei Yao","submitted_at":"2022-10-31T07:03:50Z","abstract_excerpt":"In streaming automatic speech recognition (ASR), it is desirable to reduce latency as much as possible while having minimum impact on recognition accuracy. Although a few existing methods are able to achieve this goal, they are difficult to implement due to their dependency on external alignments. In this paper, we propose a simple way to penalize symbol delay in transducer model, so that we can balance the trade-off between symbol delay and accuracy for streaming models without external alignments. Specifically, our method adds a small constant times (T/2 - t), where T is the number of frames"},"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":"2211.00490","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-10-31T07:03:50Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"130ea03d0610501ef4429561d3ae4e5abd94118469c500247d813704e3877140","abstract_canon_sha256":"335228d56b970f0b926eae93560158110dbac14cc9b8b1ff825fc6b9c2d14576"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:23.263689Z","signature_b64":"RnngZdKCcD+TUIEmHjRGw6h/RqzgJw6fxbAmzn491VXqi92qDLMTduimb0ihN+aGCfuGjgvJOMcQabHtae1sBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5315c614ff7a1ab62a33d99ac83524ae8cbec8db7b736b9c023b67c1d204855","last_reissued_at":"2026-07-05T05:12:23.263274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:23.263274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Delay-penalized transducer for low-latency streaming ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Daniel Povey, Fangjun Kuang, Liyong Guo, Long Lin, Piotr \\.Zelasko, Wei Kang, Xiaoyu Yang, Zengwei Yao","submitted_at":"2022-10-31T07:03:50Z","abstract_excerpt":"In streaming automatic speech recognition (ASR), it is desirable to reduce latency as much as possible while having minimum impact on recognition accuracy. Although a few existing methods are able to achieve this goal, they are difficult to implement due to their dependency on external alignments. In this paper, we propose a simple way to penalize symbol delay in transducer model, so that we can balance the trade-off between symbol delay and accuracy for streaming models without external alignments. Specifically, our method adds a small constant times (T/2 - t), where T is the number of frames"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.00490","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/2211.00490/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":"2211.00490","created_at":"2026-07-05T05:12:23.263344+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.00490v1","created_at":"2026-07-05T05:12:23.263344+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.00490","created_at":"2026-07-05T05:12:23.263344+00:00"},{"alias_kind":"pith_short_12","alias_value":"UUYVYYKP66Q2","created_at":"2026-07-05T05:12:23.263344+00:00"},{"alias_kind":"pith_short_16","alias_value":"UUYVYYKP66Q2WYVD","created_at":"2026-07-05T05:12:23.263344+00:00"},{"alias_kind":"pith_short_8","alias_value":"UUYVYYKP","created_at":"2026-07-05T05:12:23.263344+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/UUYVYYKP66Q2WYVDHWM2ZA2SJL","json":"https://pith.science/pith/UUYVYYKP66Q2WYVDHWM2ZA2SJL.json","graph_json":"https://pith.science/api/pith-number/UUYVYYKP66Q2WYVDHWM2ZA2SJL/graph.json","events_json":"https://pith.science/api/pith-number/UUYVYYKP66Q2WYVDHWM2ZA2SJL/events.json","paper":"https://pith.science/paper/UUYVYYKP"},"agent_actions":{"view_html":"https://pith.science/pith/UUYVYYKP66Q2WYVDHWM2ZA2SJL","download_json":"https://pith.science/pith/UUYVYYKP66Q2WYVDHWM2ZA2SJL.json","view_paper":"https://pith.science/paper/UUYVYYKP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.00490&json=true","fetch_graph":"https://pith.science/api/pith-number/UUYVYYKP66Q2WYVDHWM2ZA2SJL/graph.json","fetch_events":"https://pith.science/api/pith-number/UUYVYYKP66Q2WYVDHWM2ZA2SJL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UUYVYYKP66Q2WYVDHWM2ZA2SJL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UUYVYYKP66Q2WYVDHWM2ZA2SJL/action/storage_attestation","attest_author":"https://pith.science/pith/UUYVYYKP66Q2WYVDHWM2ZA2SJL/action/author_attestation","sign_citation":"https://pith.science/pith/UUYVYYKP66Q2WYVDHWM2ZA2SJL/action/citation_signature","submit_replication":"https://pith.science/pith/UUYVYYKP66Q2WYVDHWM2ZA2SJL/action/replication_record"}},"created_at":"2026-07-05T05:12:23.263344+00:00","updated_at":"2026-07-05T05:12:23.263344+00:00"}