{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KYVVYG5SXHB236ADQYJKXFFC3N","short_pith_number":"pith:KYVVYG5S","schema_version":"1.0","canonical_sha256":"562b5c1bb2b9c3adf8038612ab94a2db58e2eb941ff120a6279e3a391a89978e","source":{"kind":"arxiv","id":"1810.12020","version":3},"attestation_state":"computed","paper":{"title":"An improved hybrid CTC-Attention model for speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jiwei Li, Xi Zhou, Zhe Yuan, Zhuoran Lyu","submitted_at":"2018-10-29T09:28:33Z","abstract_excerpt":"Recently, end-to-end speech recognition with a hybrid model consisting of the connectionist temporal classification(CTC) and the attention encoder-decoder achieved state-of-the-art results. In this paper, we propose a novel CTC decoder structure based on the experiments we conducted and explore the relation between decoding performance and the depth of encoder. We also apply attention smoothing mechanism to acquire more context information for subword-based decoding. Taken together, these strategies allow us to achieve a word error rate(WER) of 4.43% without LM and 3.34% with RNN-LM on the tes"},"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":"1810.12020","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-10-29T09:28:33Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"f7e5eab4eff9540b39f1d411ca652a0cd2b0a9b6187fe5dd21abd1665abea16d","abstract_canon_sha256":"311e75d9cdf4118cf75992f52e0624a693c391a866f1c6aae3d777b1a9f74268"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:48.538990Z","signature_b64":"z396BKXJG9xbFatjVSkpxRywuLADccuOWl3Fhu5f0+RrNq3s4CVY8p1v+pJTjP1+V+6KCS/0M7wpFsKQ7JiCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"562b5c1bb2b9c3adf8038612ab94a2db58e2eb941ff120a6279e3a391a89978e","last_reissued_at":"2026-05-18T00:01:48.538366Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:48.538366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An improved hybrid CTC-Attention model for speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jiwei Li, Xi Zhou, Zhe Yuan, Zhuoran Lyu","submitted_at":"2018-10-29T09:28:33Z","abstract_excerpt":"Recently, end-to-end speech recognition with a hybrid model consisting of the connectionist temporal classification(CTC) and the attention encoder-decoder achieved state-of-the-art results. In this paper, we propose a novel CTC decoder structure based on the experiments we conducted and explore the relation between decoding performance and the depth of encoder. We also apply attention smoothing mechanism to acquire more context information for subword-based decoding. Taken together, these strategies allow us to achieve a word error rate(WER) of 4.43% without LM and 3.34% with RNN-LM on the tes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12020","kind":"arxiv","version":3},"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":"1810.12020","created_at":"2026-05-18T00:01:48.538468+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.12020v3","created_at":"2026-05-18T00:01:48.538468+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12020","created_at":"2026-05-18T00:01:48.538468+00:00"},{"alias_kind":"pith_short_12","alias_value":"KYVVYG5SXHB2","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KYVVYG5SXHB236AD","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KYVVYG5S","created_at":"2026-05-18T12:32:33.847187+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/KYVVYG5SXHB236ADQYJKXFFC3N","json":"https://pith.science/pith/KYVVYG5SXHB236ADQYJKXFFC3N.json","graph_json":"https://pith.science/api/pith-number/KYVVYG5SXHB236ADQYJKXFFC3N/graph.json","events_json":"https://pith.science/api/pith-number/KYVVYG5SXHB236ADQYJKXFFC3N/events.json","paper":"https://pith.science/paper/KYVVYG5S"},"agent_actions":{"view_html":"https://pith.science/pith/KYVVYG5SXHB236ADQYJKXFFC3N","download_json":"https://pith.science/pith/KYVVYG5SXHB236ADQYJKXFFC3N.json","view_paper":"https://pith.science/paper/KYVVYG5S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.12020&json=true","fetch_graph":"https://pith.science/api/pith-number/KYVVYG5SXHB236ADQYJKXFFC3N/graph.json","fetch_events":"https://pith.science/api/pith-number/KYVVYG5SXHB236ADQYJKXFFC3N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KYVVYG5SXHB236ADQYJKXFFC3N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KYVVYG5SXHB236ADQYJKXFFC3N/action/storage_attestation","attest_author":"https://pith.science/pith/KYVVYG5SXHB236ADQYJKXFFC3N/action/author_attestation","sign_citation":"https://pith.science/pith/KYVVYG5SXHB236ADQYJKXFFC3N/action/citation_signature","submit_replication":"https://pith.science/pith/KYVVYG5SXHB236ADQYJKXFFC3N/action/replication_record"}},"created_at":"2026-05-18T00:01:48.538468+00:00","updated_at":"2026-05-18T00:01:48.538468+00:00"}