{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5DOMR4EX7MQXJDTLJTA3OIRIJO","short_pith_number":"pith:5DOMR4EX","schema_version":"1.0","canonical_sha256":"e8dcc8f097fb21748e6b4cc1b722284ba12eb5ebd87fc369816d9418a186816f","source":{"kind":"arxiv","id":"2104.04702","version":2},"attestation_state":"computed","paper":{"title":"Boundary and Context Aware Training for CIF-based Non-Autoregressive End-to-end ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Fan Yu, Haoneng Luo, Leijing Hou, Lei Xie, Pengcheng Guo, Shilei Zhang, Yingying Gao, Yuhao Liang, Zhuoyuan Yao","submitted_at":"2021-04-10T07:42:27Z","abstract_excerpt":"Continuous integrate-and-fire (CIF) based models, which use a soft and monotonic alignment mechanism, have been well applied in non-autoregressive (NAR) speech recognition with competitive performance compared with other NAR methods. However, such an alignment learning strategy may suffer from an erroneous acoustic boundary estimation, severely hindering the convergence speed as well as the system performance. In this paper, we propose a boundary and context aware training approach for CIF based NAR models. Firstly, the connectionist temporal classification (CTC) spike information is utilized "},"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":"2104.04702","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-04-10T07:42:27Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"7226a4409b3b875948ae042d0fbc85adda4fec58225a1853d2d8c7c5fa010c9a","abstract_canon_sha256":"96a82eca08fc7e7dd267b37815fa83a780290b493be68beb3a932e463f9d1e54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:17:31.419176Z","signature_b64":"x7dIXIi5NVozbZyuDVlo1Q7aW233n7u1XkCnuN+43bBQh2WvPPUWoX7XOMLUrcog7/Ea0A+Hv8G+nNHcHvHlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8dcc8f097fb21748e6b4cc1b722284ba12eb5ebd87fc369816d9418a186816f","last_reissued_at":"2026-07-05T03:17:31.418699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:17:31.418699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boundary and Context Aware Training for CIF-based Non-Autoregressive End-to-end ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Fan Yu, Haoneng Luo, Leijing Hou, Lei Xie, Pengcheng Guo, Shilei Zhang, Yingying Gao, Yuhao Liang, Zhuoyuan Yao","submitted_at":"2021-04-10T07:42:27Z","abstract_excerpt":"Continuous integrate-and-fire (CIF) based models, which use a soft and monotonic alignment mechanism, have been well applied in non-autoregressive (NAR) speech recognition with competitive performance compared with other NAR methods. However, such an alignment learning strategy may suffer from an erroneous acoustic boundary estimation, severely hindering the convergence speed as well as the system performance. In this paper, we propose a boundary and context aware training approach for CIF based NAR models. Firstly, the connectionist temporal classification (CTC) spike information is utilized "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04702","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/2104.04702/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":"2104.04702","created_at":"2026-07-05T03:17:31.418757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.04702v2","created_at":"2026-07-05T03:17:31.418757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04702","created_at":"2026-07-05T03:17:31.418757+00:00"},{"alias_kind":"pith_short_12","alias_value":"5DOMR4EX7MQX","created_at":"2026-07-05T03:17:31.418757+00:00"},{"alias_kind":"pith_short_16","alias_value":"5DOMR4EX7MQXJDTL","created_at":"2026-07-05T03:17:31.418757+00:00"},{"alias_kind":"pith_short_8","alias_value":"5DOMR4EX","created_at":"2026-07-05T03:17:31.418757+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/5DOMR4EX7MQXJDTLJTA3OIRIJO","json":"https://pith.science/pith/5DOMR4EX7MQXJDTLJTA3OIRIJO.json","graph_json":"https://pith.science/api/pith-number/5DOMR4EX7MQXJDTLJTA3OIRIJO/graph.json","events_json":"https://pith.science/api/pith-number/5DOMR4EX7MQXJDTLJTA3OIRIJO/events.json","paper":"https://pith.science/paper/5DOMR4EX"},"agent_actions":{"view_html":"https://pith.science/pith/5DOMR4EX7MQXJDTLJTA3OIRIJO","download_json":"https://pith.science/pith/5DOMR4EX7MQXJDTLJTA3OIRIJO.json","view_paper":"https://pith.science/paper/5DOMR4EX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.04702&json=true","fetch_graph":"https://pith.science/api/pith-number/5DOMR4EX7MQXJDTLJTA3OIRIJO/graph.json","fetch_events":"https://pith.science/api/pith-number/5DOMR4EX7MQXJDTLJTA3OIRIJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5DOMR4EX7MQXJDTLJTA3OIRIJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5DOMR4EX7MQXJDTLJTA3OIRIJO/action/storage_attestation","attest_author":"https://pith.science/pith/5DOMR4EX7MQXJDTLJTA3OIRIJO/action/author_attestation","sign_citation":"https://pith.science/pith/5DOMR4EX7MQXJDTLJTA3OIRIJO/action/citation_signature","submit_replication":"https://pith.science/pith/5DOMR4EX7MQXJDTLJTA3OIRIJO/action/replication_record"}},"created_at":"2026-07-05T03:17:31.418757+00:00","updated_at":"2026-07-05T03:17:31.418757+00:00"}