{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EF4LJ2JOIZ2WLOZXL3ZYVXA6AO","short_pith_number":"pith:EF4LJ2JO","schema_version":"1.0","canonical_sha256":"2178b4e92e467565bb375ef38adc1e039beb9c3189dccbac18c834eab2bc8a0f","source":{"kind":"arxiv","id":"2006.01712","version":1},"attestation_state":"computed","paper":{"title":"Streaming Chunk-Aware Multihead Attention for Online End-to-End Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haoneng Luo, Jie Gao, Lei Xie, Ming Lei, Shiliang Zhang, Zhifu Gao, Zhijie Yan","submitted_at":"2020-05-21T03:35:15Z","abstract_excerpt":"Recently, streaming end-to-end automatic speech recognition (E2E-ASR) has gained more and more attention. Many efforts have been paid to turn the non-streaming attention-based E2E-ASR system into streaming architecture. In this work, we propose a novel online E2E-ASR system by using Streaming Chunk-Aware Multihead Attention(SCAMA) and a latency control memory equipped self-attention network (LC-SAN-M). LC-SAN-M uses chunk-level input to control the latency of encoder. As to SCAMA, a jointly trained predictor is used to control the output of encoder when feeding to decoder, which enables decode"},"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":"2006.01712","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-05-21T03:35:15Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"b595193182dc4a334570c7429284befb875a5bfd82941c77e68974f675d50149","abstract_canon_sha256":"886a40d255f1cd85e2aafd912ecaa4d9048228cf0e4d8f1d42455e276a7c7a88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:07:33.413189Z","signature_b64":"CIszB/zgowQo1lVyA15O2TMzTlmHWXxtqCci/QqnfaFLPLlM9PbRI7ctUF98/QvYPMF0CBSXPsXmlLz/AY0fAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2178b4e92e467565bb375ef38adc1e039beb9c3189dccbac18c834eab2bc8a0f","last_reissued_at":"2026-07-05T01:07:33.412808Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:07:33.412808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Streaming Chunk-Aware Multihead Attention for Online End-to-End Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haoneng Luo, Jie Gao, Lei Xie, Ming Lei, Shiliang Zhang, Zhifu Gao, Zhijie Yan","submitted_at":"2020-05-21T03:35:15Z","abstract_excerpt":"Recently, streaming end-to-end automatic speech recognition (E2E-ASR) has gained more and more attention. Many efforts have been paid to turn the non-streaming attention-based E2E-ASR system into streaming architecture. In this work, we propose a novel online E2E-ASR system by using Streaming Chunk-Aware Multihead Attention(SCAMA) and a latency control memory equipped self-attention network (LC-SAN-M). LC-SAN-M uses chunk-level input to control the latency of encoder. As to SCAMA, a jointly trained predictor is used to control the output of encoder when feeding to decoder, which enables decode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.01712","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/2006.01712/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":"2006.01712","created_at":"2026-07-05T01:07:33.412872+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.01712v1","created_at":"2026-07-05T01:07:33.412872+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.01712","created_at":"2026-07-05T01:07:33.412872+00:00"},{"alias_kind":"pith_short_12","alias_value":"EF4LJ2JOIZ2W","created_at":"2026-07-05T01:07:33.412872+00:00"},{"alias_kind":"pith_short_16","alias_value":"EF4LJ2JOIZ2WLOZX","created_at":"2026-07-05T01:07:33.412872+00:00"},{"alias_kind":"pith_short_8","alias_value":"EF4LJ2JO","created_at":"2026-07-05T01:07:33.412872+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/EF4LJ2JOIZ2WLOZXL3ZYVXA6AO","json":"https://pith.science/pith/EF4LJ2JOIZ2WLOZXL3ZYVXA6AO.json","graph_json":"https://pith.science/api/pith-number/EF4LJ2JOIZ2WLOZXL3ZYVXA6AO/graph.json","events_json":"https://pith.science/api/pith-number/EF4LJ2JOIZ2WLOZXL3ZYVXA6AO/events.json","paper":"https://pith.science/paper/EF4LJ2JO"},"agent_actions":{"view_html":"https://pith.science/pith/EF4LJ2JOIZ2WLOZXL3ZYVXA6AO","download_json":"https://pith.science/pith/EF4LJ2JOIZ2WLOZXL3ZYVXA6AO.json","view_paper":"https://pith.science/paper/EF4LJ2JO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.01712&json=true","fetch_graph":"https://pith.science/api/pith-number/EF4LJ2JOIZ2WLOZXL3ZYVXA6AO/graph.json","fetch_events":"https://pith.science/api/pith-number/EF4LJ2JOIZ2WLOZXL3ZYVXA6AO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EF4LJ2JOIZ2WLOZXL3ZYVXA6AO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EF4LJ2JOIZ2WLOZXL3ZYVXA6AO/action/storage_attestation","attest_author":"https://pith.science/pith/EF4LJ2JOIZ2WLOZXL3ZYVXA6AO/action/author_attestation","sign_citation":"https://pith.science/pith/EF4LJ2JOIZ2WLOZXL3ZYVXA6AO/action/citation_signature","submit_replication":"https://pith.science/pith/EF4LJ2JOIZ2WLOZXL3ZYVXA6AO/action/replication_record"}},"created_at":"2026-07-05T01:07:33.412872+00:00","updated_at":"2026-07-05T01:07:33.412872+00:00"}