{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XF3R7BJVTDHEMRWESAASU6WRGM","short_pith_number":"pith:XF3R7BJV","schema_version":"1.0","canonical_sha256":"b9771f853598ce4646c490012a7ad13322071b70541234175f0196b7215c7026","source":{"kind":"arxiv","id":"1810.12001","version":2},"attestation_state":"computed","paper":{"title":"Cascaded CNN-resBiLSTM-CTC: An End-to-End Acoustic Model For Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jiwei Li, Xinpei Zhou, Xi Zhou","submitted_at":"2018-10-29T08:52:31Z","abstract_excerpt":"Automatic speech recognition (ASR) tasks are resolved by end-to-end deep learning models, which benefits us by less preparation of raw data, and easier transformation between languages. We propose a novel end-to-end deep learning model architecture namely cascaded CNN-resBiLSTM-CTC. In the proposed model, we add residual blocks in BiLSTM layers to extract sophisticated phoneme and semantic information together, and apply cascaded structure to pay more attention mining information of hard negative samples. By applying both simple Fast Fourier Transform (FFT) technique and n-gram language model "},"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":"1810.12001","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-10-29T08:52:31Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"2ef07a2d314d29a285c968ea9e9cf1ebdb7b31a7e51d0a17401019c3261537ea","abstract_canon_sha256":"3c08dcefdc874b8927c5ea24833939821eb9b498216edb786803a5f0920d99a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:57.020346Z","signature_b64":"YlRvKxbeyX+s5FfigsklyodBwowTkE9qd1TjNV+GhJc2IcOZ1FYNMLsO2+I95ao0jTvIHNKig8Nsig5ZXtkjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9771f853598ce4646c490012a7ad13322071b70541234175f0196b7215c7026","last_reissued_at":"2026-05-18T00:01:57.019609Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:57.019609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cascaded CNN-resBiLSTM-CTC: An End-to-End Acoustic Model For Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jiwei Li, Xinpei Zhou, Xi Zhou","submitted_at":"2018-10-29T08:52:31Z","abstract_excerpt":"Automatic speech recognition (ASR) tasks are resolved by end-to-end deep learning models, which benefits us by less preparation of raw data, and easier transformation between languages. We propose a novel end-to-end deep learning model architecture namely cascaded CNN-resBiLSTM-CTC. In the proposed model, we add residual blocks in BiLSTM layers to extract sophisticated phoneme and semantic information together, and apply cascaded structure to pay more attention mining information of hard negative samples. By applying both simple Fast Fourier Transform (FFT) technique and n-gram language model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12001","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":"1810.12001","created_at":"2026-05-18T00:01:57.019733+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.12001v2","created_at":"2026-05-18T00:01:57.019733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12001","created_at":"2026-05-18T00:01:57.019733+00:00"},{"alias_kind":"pith_short_12","alias_value":"XF3R7BJVTDHE","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"XF3R7BJVTDHEMRWE","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"XF3R7BJV","created_at":"2026-05-18T12:33:01.666342+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/XF3R7BJVTDHEMRWESAASU6WRGM","json":"https://pith.science/pith/XF3R7BJVTDHEMRWESAASU6WRGM.json","graph_json":"https://pith.science/api/pith-number/XF3R7BJVTDHEMRWESAASU6WRGM/graph.json","events_json":"https://pith.science/api/pith-number/XF3R7BJVTDHEMRWESAASU6WRGM/events.json","paper":"https://pith.science/paper/XF3R7BJV"},"agent_actions":{"view_html":"https://pith.science/pith/XF3R7BJVTDHEMRWESAASU6WRGM","download_json":"https://pith.science/pith/XF3R7BJVTDHEMRWESAASU6WRGM.json","view_paper":"https://pith.science/paper/XF3R7BJV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.12001&json=true","fetch_graph":"https://pith.science/api/pith-number/XF3R7BJVTDHEMRWESAASU6WRGM/graph.json","fetch_events":"https://pith.science/api/pith-number/XF3R7BJVTDHEMRWESAASU6WRGM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XF3R7BJVTDHEMRWESAASU6WRGM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XF3R7BJVTDHEMRWESAASU6WRGM/action/storage_attestation","attest_author":"https://pith.science/pith/XF3R7BJVTDHEMRWESAASU6WRGM/action/author_attestation","sign_citation":"https://pith.science/pith/XF3R7BJVTDHEMRWESAASU6WRGM/action/citation_signature","submit_replication":"https://pith.science/pith/XF3R7BJVTDHEMRWESAASU6WRGM/action/replication_record"}},"created_at":"2026-05-18T00:01:57.019733+00:00","updated_at":"2026-05-18T00:01:57.019733+00:00"}