{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:V4QBXEXYELHQK4R32DTOS533X5","short_pith_number":"pith:V4QBXEXY","schema_version":"1.0","canonical_sha256":"af201b92f822cf05723bd0e6e9777bbf7f8ad9a6f6f38daca4f1d9378190482e","source":{"kind":"arxiv","id":"1807.04978","version":2},"attestation_state":"computed","paper":{"title":"Hybrid CTC-Attention based End-to-End Speech Recognition using Subword Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Hui Lin, Wei Chu, Zhangyu Xiao, Zhijian Ou","submitted_at":"2018-07-13T09:06:07Z","abstract_excerpt":"In this paper, we present an end-to-end automatic speech recognition system, which successfully employs subword units in a hybrid CTC-Attention based system. The subword units are obtained by the byte-pair encoding (BPE) compression algorithm. Compared to using words as modeling units, using characters or subword units does not suffer from the out-of-vocabulary (OOV) problem. Furthermore, using subword units further offers a capability in modeling longer context than using characters. We evaluate different systems over the LibriSpeech 1000h dataset. The subword-based hybrid CTC-Attention syste"},"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":"1807.04978","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-07-13T09:06:07Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"f17981b29bfd5b89d59acaf02109eb950b6018412d847c3b036b865d43c4a57d","abstract_canon_sha256":"cffa0c013d9017aee4b63c07ff104c0596416810c39d06fbfb7dc410a39257d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:24.601310Z","signature_b64":"CqlcRi+vNeCNUteqXQ549G3UV22hIyl8gB66hOcjxoJaLksRj0689A3cxdvdiSxVHb5JFUTuLWWfsHirt041BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af201b92f822cf05723bd0e6e9777bbf7f8ad9a6f6f38daca4f1d9378190482e","last_reissued_at":"2026-05-18T00:06:24.600653Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:24.600653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hybrid CTC-Attention based End-to-End Speech Recognition using Subword Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Hui Lin, Wei Chu, Zhangyu Xiao, Zhijian Ou","submitted_at":"2018-07-13T09:06:07Z","abstract_excerpt":"In this paper, we present an end-to-end automatic speech recognition system, which successfully employs subword units in a hybrid CTC-Attention based system. The subword units are obtained by the byte-pair encoding (BPE) compression algorithm. Compared to using words as modeling units, using characters or subword units does not suffer from the out-of-vocabulary (OOV) problem. Furthermore, using subword units further offers a capability in modeling longer context than using characters. We evaluate different systems over the LibriSpeech 1000h dataset. The subword-based hybrid CTC-Attention syste"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.04978","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":""},"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":"1807.04978","created_at":"2026-05-18T00:06:24.600736+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.04978v2","created_at":"2026-05-18T00:06:24.600736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.04978","created_at":"2026-05-18T00:06:24.600736+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4QBXEXYELHQ","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4QBXEXYELHQK4R3","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4QBXEXY","created_at":"2026-05-18T12:32:56.356000+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/V4QBXEXYELHQK4R32DTOS533X5","json":"https://pith.science/pith/V4QBXEXYELHQK4R32DTOS533X5.json","graph_json":"https://pith.science/api/pith-number/V4QBXEXYELHQK4R32DTOS533X5/graph.json","events_json":"https://pith.science/api/pith-number/V4QBXEXYELHQK4R32DTOS533X5/events.json","paper":"https://pith.science/paper/V4QBXEXY"},"agent_actions":{"view_html":"https://pith.science/pith/V4QBXEXYELHQK4R32DTOS533X5","download_json":"https://pith.science/pith/V4QBXEXYELHQK4R32DTOS533X5.json","view_paper":"https://pith.science/paper/V4QBXEXY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.04978&json=true","fetch_graph":"https://pith.science/api/pith-number/V4QBXEXYELHQK4R32DTOS533X5/graph.json","fetch_events":"https://pith.science/api/pith-number/V4QBXEXYELHQK4R32DTOS533X5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4QBXEXYELHQK4R32DTOS533X5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4QBXEXYELHQK4R32DTOS533X5/action/storage_attestation","attest_author":"https://pith.science/pith/V4QBXEXYELHQK4R32DTOS533X5/action/author_attestation","sign_citation":"https://pith.science/pith/V4QBXEXYELHQK4R32DTOS533X5/action/citation_signature","submit_replication":"https://pith.science/pith/V4QBXEXYELHQK4R32DTOS533X5/action/replication_record"}},"created_at":"2026-05-18T00:06:24.600736+00:00","updated_at":"2026-05-18T00:06:24.600736+00:00"}