{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LJVA6OASPFE6JXUODWI4O4YJIE","short_pith_number":"pith:LJVA6OAS","schema_version":"1.0","canonical_sha256":"5a6a0f38127949e4de8e1d91c77309413195de034b06c78308d68936c4d7d9be","source":{"kind":"arxiv","id":"1903.05261","version":1},"attestation_state":"computed","paper":{"title":"End-To-End Speech Recognition Using A High Rank LSTM-CTC Based Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mei-Yuh Hwang, Xin Lei, Yangyang Shi","submitted_at":"2019-03-12T23:40:27Z","abstract_excerpt":"Long Short Term Memory Connectionist Temporal Classification (LSTM-CTC) based end-to-end models are widely used in speech recognition due to its simplicity in training and efficiency in decoding. In conventional LSTM-CTC based models, a bottleneck projection matrix maps the hidden feature vectors obtained from LSTM to softmax output layer. In this paper, we propose to use a high rank projection layer to replace the projection matrix. The output from the high rank projection layer is a weighted combination of vectors that are projected from the hidden feature vectors via different projection ma"},"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":"1903.05261","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-12T23:40:27Z","cross_cats_sorted":[],"title_canon_sha256":"a597671f1ba72c7a9c3af236c8b0106ab8cd3a9cba77a0a5e10dd85cc685aa2f","abstract_canon_sha256":"fb7f97f5a69abb471fb2676334ac9d509687f40b0b455b3da03de22ac11e9665"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:24.874383Z","signature_b64":"qfeRhq8Uv8L7kHYXHTNzvjGk/WiuzmOm19W5qDN/noqs6Qh+kMl/Fha7jar89PXOjygrz2i/UQJVySFsV2ZfDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a6a0f38127949e4de8e1d91c77309413195de034b06c78308d68936c4d7d9be","last_reissued_at":"2026-05-17T23:51:24.873721Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:24.873721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-To-End Speech Recognition Using A High Rank LSTM-CTC Based Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mei-Yuh Hwang, Xin Lei, Yangyang Shi","submitted_at":"2019-03-12T23:40:27Z","abstract_excerpt":"Long Short Term Memory Connectionist Temporal Classification (LSTM-CTC) based end-to-end models are widely used in speech recognition due to its simplicity in training and efficiency in decoding. In conventional LSTM-CTC based models, a bottleneck projection matrix maps the hidden feature vectors obtained from LSTM to softmax output layer. In this paper, we propose to use a high rank projection layer to replace the projection matrix. The output from the high rank projection layer is a weighted combination of vectors that are projected from the hidden feature vectors via different projection ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.05261","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":"1903.05261","created_at":"2026-05-17T23:51:24.873815+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.05261v1","created_at":"2026-05-17T23:51:24.873815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.05261","created_at":"2026-05-17T23:51:24.873815+00:00"},{"alias_kind":"pith_short_12","alias_value":"LJVA6OASPFE6","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"LJVA6OASPFE6JXUO","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"LJVA6OAS","created_at":"2026-05-18T12:33:21.387695+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/LJVA6OASPFE6JXUODWI4O4YJIE","json":"https://pith.science/pith/LJVA6OASPFE6JXUODWI4O4YJIE.json","graph_json":"https://pith.science/api/pith-number/LJVA6OASPFE6JXUODWI4O4YJIE/graph.json","events_json":"https://pith.science/api/pith-number/LJVA6OASPFE6JXUODWI4O4YJIE/events.json","paper":"https://pith.science/paper/LJVA6OAS"},"agent_actions":{"view_html":"https://pith.science/pith/LJVA6OASPFE6JXUODWI4O4YJIE","download_json":"https://pith.science/pith/LJVA6OASPFE6JXUODWI4O4YJIE.json","view_paper":"https://pith.science/paper/LJVA6OAS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.05261&json=true","fetch_graph":"https://pith.science/api/pith-number/LJVA6OASPFE6JXUODWI4O4YJIE/graph.json","fetch_events":"https://pith.science/api/pith-number/LJVA6OASPFE6JXUODWI4O4YJIE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LJVA6OASPFE6JXUODWI4O4YJIE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LJVA6OASPFE6JXUODWI4O4YJIE/action/storage_attestation","attest_author":"https://pith.science/pith/LJVA6OASPFE6JXUODWI4O4YJIE/action/author_attestation","sign_citation":"https://pith.science/pith/LJVA6OASPFE6JXUODWI4O4YJIE/action/citation_signature","submit_replication":"https://pith.science/pith/LJVA6OASPFE6JXUODWI4O4YJIE/action/replication_record"}},"created_at":"2026-05-17T23:51:24.873815+00:00","updated_at":"2026-05-17T23:51:24.873815+00:00"}