{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:INUIC3776ICTVBAD3QIAHOAB7K","short_pith_number":"pith:INUIC377","schema_version":"1.0","canonical_sha256":"4368816ffff2053a8403dc1003b801fabd2b823bc5815e37998ab27d3debb9fa","source":{"kind":"arxiv","id":"1904.13377","version":2},"attestation_state":"computed","paper":{"title":"Very Deep Self-Attention Networks for End-to-End Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alexander Waibel, Jan Niehues, Markus M\\\"uller, Ngoc-Quan Pham, Sebastian St\\\"uker, Thai-Son Nguyen","submitted_at":"2019-04-30T17:20:32Z","abstract_excerpt":"Recently, end-to-end sequence-to-sequence models for speech recognition have gained significant interest in the research community. While previous architecture choices revolve around time-delay neural networks (TDNN) and long short-term memory (LSTM) recurrent neural networks, we propose to use self-attention via the Transformer architecture as an alternative. Our analysis shows that deep Transformer networks with high learning capacity are able to exceed performance from previous end-to-end approaches and even match the conventional hybrid systems. Moreover, we trained very deep models with u"},"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":"1904.13377","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-30T17:20:32Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"eaa989ca5d934fc133381f5dcfdd12bca68ac89ff9fa036ba02e386056373e76","abstract_canon_sha256":"7fabfa3a92d8a1a1ec3c1699c57bd9acb15918edadc8f567e89d9ef67b1cf915"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:06.916535Z","signature_b64":"AH4Ez3wSOjKhUuVj1r8d2WcZlyXyZ8ueZH+QNGJLLdRsLCqhttr99bfWGd8Pg8HpfV6DIbcaZXvDUO9STd+YDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4368816ffff2053a8403dc1003b801fabd2b823bc5815e37998ab27d3debb9fa","last_reissued_at":"2026-05-17T23:47:06.915850Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:06.915850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Very Deep Self-Attention Networks for End-to-End Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alexander Waibel, Jan Niehues, Markus M\\\"uller, Ngoc-Quan Pham, Sebastian St\\\"uker, Thai-Son Nguyen","submitted_at":"2019-04-30T17:20:32Z","abstract_excerpt":"Recently, end-to-end sequence-to-sequence models for speech recognition have gained significant interest in the research community. While previous architecture choices revolve around time-delay neural networks (TDNN) and long short-term memory (LSTM) recurrent neural networks, we propose to use self-attention via the Transformer architecture as an alternative. Our analysis shows that deep Transformer networks with high learning capacity are able to exceed performance from previous end-to-end approaches and even match the conventional hybrid systems. Moreover, we trained very deep models with u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.13377","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":"1904.13377","created_at":"2026-05-17T23:47:06.915960+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.13377v2","created_at":"2026-05-17T23:47:06.915960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.13377","created_at":"2026-05-17T23:47:06.915960+00:00"},{"alias_kind":"pith_short_12","alias_value":"INUIC3776ICT","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"INUIC3776ICTVBAD","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"INUIC377","created_at":"2026-05-18T12:33:18.533446+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/INUIC3776ICTVBAD3QIAHOAB7K","json":"https://pith.science/pith/INUIC3776ICTVBAD3QIAHOAB7K.json","graph_json":"https://pith.science/api/pith-number/INUIC3776ICTVBAD3QIAHOAB7K/graph.json","events_json":"https://pith.science/api/pith-number/INUIC3776ICTVBAD3QIAHOAB7K/events.json","paper":"https://pith.science/paper/INUIC377"},"agent_actions":{"view_html":"https://pith.science/pith/INUIC3776ICTVBAD3QIAHOAB7K","download_json":"https://pith.science/pith/INUIC3776ICTVBAD3QIAHOAB7K.json","view_paper":"https://pith.science/paper/INUIC377","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.13377&json=true","fetch_graph":"https://pith.science/api/pith-number/INUIC3776ICTVBAD3QIAHOAB7K/graph.json","fetch_events":"https://pith.science/api/pith-number/INUIC3776ICTVBAD3QIAHOAB7K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INUIC3776ICTVBAD3QIAHOAB7K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INUIC3776ICTVBAD3QIAHOAB7K/action/storage_attestation","attest_author":"https://pith.science/pith/INUIC3776ICTVBAD3QIAHOAB7K/action/author_attestation","sign_citation":"https://pith.science/pith/INUIC3776ICTVBAD3QIAHOAB7K/action/citation_signature","submit_replication":"https://pith.science/pith/INUIC3776ICTVBAD3QIAHOAB7K/action/replication_record"}},"created_at":"2026-05-17T23:47:06.915960+00:00","updated_at":"2026-05-17T23:47:06.915960+00:00"}