{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:7X36TUBAE7VUCCNCW3JYCEIQMM","short_pith_number":"pith:7X36TUBA","schema_version":"1.0","canonical_sha256":"fdf7e9d02027eb4109a2b6d3811110632a925b5a5a856c0c38443fda7661fd36","source":{"kind":"arxiv","id":"1811.04568","version":1},"attestation_state":"computed","paper":{"title":"Vectorization of hypotheses and speech for faster beam search in encoder decoder-based speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"Hiroshi Seki, Shinji Watanabe, Takaaki Hori","submitted_at":"2018-11-12T06:02:19Z","abstract_excerpt":"Attention-based encoder decoder network uses a left-to-right beam search algorithm in the inference step. The current beam search expands hypotheses and traverses the expanded hypotheses at the next time step. This traversal is implemented using a for-loop program in general, and it leads to speed down of the recognition process. In this paper, we propose a parallelism technique for beam search, which accelerates the search process by vectorizing multiple hypotheses to eliminate the for-loop program. We also propose a technique to batch multiple speech utterances for off-line recognition use, "},"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":"1811.04568","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-11-12T06:02:19Z","cross_cats_sorted":["cs.CL","eess.AS","stat.ML"],"title_canon_sha256":"05a480ffc47137d786c036277a673a6c68d48d71aeae66d5952c01937939da8c","abstract_canon_sha256":"febf2254e8f8b27ca5bb564a5e6127733d1a7776f79ec732a90f904c3f98156a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:04.741402Z","signature_b64":"hgNuE+1+JkeXLEOZQ9Z8Ub03RF2CbSVgyZmpbTX9aT/k+Ji6tHWvawBcueHWHGglPxnxj83mFwmhwXdqHcEICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdf7e9d02027eb4109a2b6d3811110632a925b5a5a856c0c38443fda7661fd36","last_reissued_at":"2026-05-18T00:01:04.740822Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:04.740822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vectorization of hypotheses and speech for faster beam search in encoder decoder-based speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"Hiroshi Seki, Shinji Watanabe, Takaaki Hori","submitted_at":"2018-11-12T06:02:19Z","abstract_excerpt":"Attention-based encoder decoder network uses a left-to-right beam search algorithm in the inference step. The current beam search expands hypotheses and traverses the expanded hypotheses at the next time step. This traversal is implemented using a for-loop program in general, and it leads to speed down of the recognition process. In this paper, we propose a parallelism technique for beam search, which accelerates the search process by vectorizing multiple hypotheses to eliminate the for-loop program. We also propose a technique to batch multiple speech utterances for off-line recognition use, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.04568","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":"1811.04568","created_at":"2026-05-18T00:01:04.740903+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.04568v1","created_at":"2026-05-18T00:01:04.740903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.04568","created_at":"2026-05-18T00:01:04.740903+00:00"},{"alias_kind":"pith_short_12","alias_value":"7X36TUBAE7VU","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"7X36TUBAE7VUCCNC","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"7X36TUBA","created_at":"2026-05-18T12:32:11.075285+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/7X36TUBAE7VUCCNCW3JYCEIQMM","json":"https://pith.science/pith/7X36TUBAE7VUCCNCW3JYCEIQMM.json","graph_json":"https://pith.science/api/pith-number/7X36TUBAE7VUCCNCW3JYCEIQMM/graph.json","events_json":"https://pith.science/api/pith-number/7X36TUBAE7VUCCNCW3JYCEIQMM/events.json","paper":"https://pith.science/paper/7X36TUBA"},"agent_actions":{"view_html":"https://pith.science/pith/7X36TUBAE7VUCCNCW3JYCEIQMM","download_json":"https://pith.science/pith/7X36TUBAE7VUCCNCW3JYCEIQMM.json","view_paper":"https://pith.science/paper/7X36TUBA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.04568&json=true","fetch_graph":"https://pith.science/api/pith-number/7X36TUBAE7VUCCNCW3JYCEIQMM/graph.json","fetch_events":"https://pith.science/api/pith-number/7X36TUBAE7VUCCNCW3JYCEIQMM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7X36TUBAE7VUCCNCW3JYCEIQMM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7X36TUBAE7VUCCNCW3JYCEIQMM/action/storage_attestation","attest_author":"https://pith.science/pith/7X36TUBAE7VUCCNCW3JYCEIQMM/action/author_attestation","sign_citation":"https://pith.science/pith/7X36TUBAE7VUCCNCW3JYCEIQMM/action/citation_signature","submit_replication":"https://pith.science/pith/7X36TUBAE7VUCCNCW3JYCEIQMM/action/replication_record"}},"created_at":"2026-05-18T00:01:04.740903+00:00","updated_at":"2026-05-18T00:01:04.740903+00:00"}