{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QBJZLO7DOMKNK22IUX7PF7BCC6","short_pith_number":"pith:QBJZLO7D","schema_version":"1.0","canonical_sha256":"805395bbe37314d56b48a5fef2fc2217a4421f62c3c25f81bd9535efe207931b","source":{"kind":"arxiv","id":"1902.06450","version":1},"attestation_state":"computed","paper":{"title":"Self-Attention Aligner: A Latency-Control End-to-End Model for ASR Using Self-Attention Network and Chunk-Hopping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bo Xu, Feng Wang, Linhao Dong","submitted_at":"2019-02-18T08:17:24Z","abstract_excerpt":"Self-attention network, an attention-based feedforward neural network, has recently shown the potential to replace recurrent neural networks (RNNs) in a variety of NLP tasks. However, it is not clear if the self-attention network could be a good alternative of RNNs in automatic speech recognition (ASR), which processes the longer speech sequences and may have online recognition requirements. In this paper, we present a RNN-free end-to-end model: self-attention aligner (SAA), which applies the self-attention networks to a simplified recurrent neural aligner (RNA) framework. We also propose a ch"},"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":"1902.06450","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-18T08:17:24Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"5fd634048ffa2d0e8cd8fd37fe1f91170445e4176d9f17e4b30baf1407541e79","abstract_canon_sha256":"d4abafca291f7ceeb1adef45253f22c1c09a813b03f6531331fa949df01125e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:45.455532Z","signature_b64":"3Uy6sLLzHCd0JbTfYcbD+y6KjPw+VKYlVwFsNklOf6FzW4lg384nMS+At5BWrm6NgJRXLitcH37xJscMWaNBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"805395bbe37314d56b48a5fef2fc2217a4421f62c3c25f81bd9535efe207931b","last_reissued_at":"2026-05-17T23:53:45.454778Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:45.454778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Attention Aligner: A Latency-Control End-to-End Model for ASR Using Self-Attention Network and Chunk-Hopping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bo Xu, Feng Wang, Linhao Dong","submitted_at":"2019-02-18T08:17:24Z","abstract_excerpt":"Self-attention network, an attention-based feedforward neural network, has recently shown the potential to replace recurrent neural networks (RNNs) in a variety of NLP tasks. However, it is not clear if the self-attention network could be a good alternative of RNNs in automatic speech recognition (ASR), which processes the longer speech sequences and may have online recognition requirements. In this paper, we present a RNN-free end-to-end model: self-attention aligner (SAA), which applies the self-attention networks to a simplified recurrent neural aligner (RNA) framework. We also propose a ch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.06450","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":""},"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":"1902.06450","created_at":"2026-05-17T23:53:45.454899+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.06450v1","created_at":"2026-05-17T23:53:45.454899+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.06450","created_at":"2026-05-17T23:53:45.454899+00:00"},{"alias_kind":"pith_short_12","alias_value":"QBJZLO7DOMKN","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"QBJZLO7DOMKNK22I","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"QBJZLO7D","created_at":"2026-05-18T12:33:27.125529+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/QBJZLO7DOMKNK22IUX7PF7BCC6","json":"https://pith.science/pith/QBJZLO7DOMKNK22IUX7PF7BCC6.json","graph_json":"https://pith.science/api/pith-number/QBJZLO7DOMKNK22IUX7PF7BCC6/graph.json","events_json":"https://pith.science/api/pith-number/QBJZLO7DOMKNK22IUX7PF7BCC6/events.json","paper":"https://pith.science/paper/QBJZLO7D"},"agent_actions":{"view_html":"https://pith.science/pith/QBJZLO7DOMKNK22IUX7PF7BCC6","download_json":"https://pith.science/pith/QBJZLO7DOMKNK22IUX7PF7BCC6.json","view_paper":"https://pith.science/paper/QBJZLO7D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.06450&json=true","fetch_graph":"https://pith.science/api/pith-number/QBJZLO7DOMKNK22IUX7PF7BCC6/graph.json","fetch_events":"https://pith.science/api/pith-number/QBJZLO7DOMKNK22IUX7PF7BCC6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QBJZLO7DOMKNK22IUX7PF7BCC6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QBJZLO7DOMKNK22IUX7PF7BCC6/action/storage_attestation","attest_author":"https://pith.science/pith/QBJZLO7DOMKNK22IUX7PF7BCC6/action/author_attestation","sign_citation":"https://pith.science/pith/QBJZLO7DOMKNK22IUX7PF7BCC6/action/citation_signature","submit_replication":"https://pith.science/pith/QBJZLO7DOMKNK22IUX7PF7BCC6/action/replication_record"}},"created_at":"2026-05-17T23:53:45.454899+00:00","updated_at":"2026-05-17T23:53:45.454899+00:00"}