{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LXAQ2CW72SXGTFCMOS5VE56S36","short_pith_number":"pith:LXAQ2CW7","schema_version":"1.0","canonical_sha256":"5dc10d0adfd4ae69944c74bb5277d2df8f05a7cc7c33be12ad0179e05606613b","source":{"kind":"arxiv","id":"2008.05514","version":2},"attestation_state":"computed","paper":{"title":"Online Automatic Speech Recognition with Listen, Attend and Spell Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Arnab Ghoshal, Dogan Can, Roger Hsiao, Ruchir Travadi, Tim Ng","submitted_at":"2020-08-12T18:18:54Z","abstract_excerpt":"The Listen, Attend and Spell (LAS) model and other attention-based automatic speech recognition (ASR) models have known limitations when operated in a fully online mode. In this paper, we analyze the online operation of LAS models to demonstrate that these limitations stem from the handling of silence regions and the reliability of online attention mechanism at the edge of input buffers. We propose a novel and simple technique that can achieve fully online recognition while meeting accuracy and latency targets. For the Mandarin dictation task, our proposed approach can achieve a character erro"},"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":"2008.05514","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-12T18:18:54Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"2abce11b0246361d658866d09dabba416f29a9a8f2abbd94b0a42ffd6375b71a","abstract_canon_sha256":"092972c7fe24570067091ec4efe1df9f5ec5672ae3f8d780e5efac7af6ae9da7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:05.481194Z","signature_b64":"nmwwr5KRWov9iI8VJZ67ng+4iMEL7jPhql/CImYosyMHsI8geiZr9hlpS0jvRshtl16zEKpokdU8nqD4jSLVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5dc10d0adfd4ae69944c74bb5277d2df8f05a7cc7c33be12ad0179e05606613b","last_reissued_at":"2026-07-05T01:56:05.480710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:05.480710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Automatic Speech Recognition with Listen, Attend and Spell Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Arnab Ghoshal, Dogan Can, Roger Hsiao, Ruchir Travadi, Tim Ng","submitted_at":"2020-08-12T18:18:54Z","abstract_excerpt":"The Listen, Attend and Spell (LAS) model and other attention-based automatic speech recognition (ASR) models have known limitations when operated in a fully online mode. In this paper, we analyze the online operation of LAS models to demonstrate that these limitations stem from the handling of silence regions and the reliability of online attention mechanism at the edge of input buffers. We propose a novel and simple technique that can achieve fully online recognition while meeting accuracy and latency targets. For the Mandarin dictation task, our proposed approach can achieve a character erro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.05514","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/2008.05514/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":"2008.05514","created_at":"2026-07-05T01:56:05.480778+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.05514v2","created_at":"2026-07-05T01:56:05.480778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.05514","created_at":"2026-07-05T01:56:05.480778+00:00"},{"alias_kind":"pith_short_12","alias_value":"LXAQ2CW72SXG","created_at":"2026-07-05T01:56:05.480778+00:00"},{"alias_kind":"pith_short_16","alias_value":"LXAQ2CW72SXGTFCM","created_at":"2026-07-05T01:56:05.480778+00:00"},{"alias_kind":"pith_short_8","alias_value":"LXAQ2CW7","created_at":"2026-07-05T01:56:05.480778+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/LXAQ2CW72SXGTFCMOS5VE56S36","json":"https://pith.science/pith/LXAQ2CW72SXGTFCMOS5VE56S36.json","graph_json":"https://pith.science/api/pith-number/LXAQ2CW72SXGTFCMOS5VE56S36/graph.json","events_json":"https://pith.science/api/pith-number/LXAQ2CW72SXGTFCMOS5VE56S36/events.json","paper":"https://pith.science/paper/LXAQ2CW7"},"agent_actions":{"view_html":"https://pith.science/pith/LXAQ2CW72SXGTFCMOS5VE56S36","download_json":"https://pith.science/pith/LXAQ2CW72SXGTFCMOS5VE56S36.json","view_paper":"https://pith.science/paper/LXAQ2CW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.05514&json=true","fetch_graph":"https://pith.science/api/pith-number/LXAQ2CW72SXGTFCMOS5VE56S36/graph.json","fetch_events":"https://pith.science/api/pith-number/LXAQ2CW72SXGTFCMOS5VE56S36/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LXAQ2CW72SXGTFCMOS5VE56S36/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LXAQ2CW72SXGTFCMOS5VE56S36/action/storage_attestation","attest_author":"https://pith.science/pith/LXAQ2CW72SXGTFCMOS5VE56S36/action/author_attestation","sign_citation":"https://pith.science/pith/LXAQ2CW72SXGTFCMOS5VE56S36/action/citation_signature","submit_replication":"https://pith.science/pith/LXAQ2CW72SXGTFCMOS5VE56S36/action/replication_record"}},"created_at":"2026-07-05T01:56:05.480778+00:00","updated_at":"2026-07-05T01:56:05.480778+00:00"}