{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:YNICFBLWSL34HBR325PSGLDKWR","short_pith_number":"pith:YNICFBLW","schema_version":"1.0","canonical_sha256":"c35022857692f7c3863bd75f232c6ab44d8604e58dca3b2f19329083558f50af","source":{"kind":"arxiv","id":"1705.05992","version":1},"attestation_state":"computed","paper":{"title":"Frame Stacking and Retaining for Recurrent Neural Network Acoustic Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Juan Wei, Jun Zhang, Xu Tian, Yi He, Zejun Ma","submitted_at":"2017-05-17T02:34:27Z","abstract_excerpt":"Frame stacking is broadly applied in end-to-end neural network training like connectionist temporal classification (CTC), and it leads to more accurate models and faster decoding. However, it is not well-suited to conventional neural network based on context-dependent state acoustic model, if the decoder is unchanged. In this paper, we propose a novel frame retaining method which is applied in decoding. The system which combined frame retaining with frame stacking could reduces the time consumption of both training and decoding. Long short-term memory (LSTM) recurrent neural networks (RNNs) us"},"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":"1705.05992","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-17T02:34:27Z","cross_cats_sorted":[],"title_canon_sha256":"bdfb5cfd736c1292af867d212a7be2a70155a0b0e4d612e3a2fcfa48976fa1cd","abstract_canon_sha256":"a98d44512080f74d27a9cdae335e1bda58193ef404db8166514d6c5280d61750"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:19.267536Z","signature_b64":"KFXhslO0YYA9Ry3DfHLEc+djiPTkS5bo0yA/yZuFMUn0bf/BEA6Fcf8Ymui1oKgxu2g8xHYsGWhlvIXArJnXAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c35022857692f7c3863bd75f232c6ab44d8604e58dca3b2f19329083558f50af","last_reissued_at":"2026-05-18T00:44:19.267067Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:19.267067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Frame Stacking and Retaining for Recurrent Neural Network Acoustic Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Juan Wei, Jun Zhang, Xu Tian, Yi He, Zejun Ma","submitted_at":"2017-05-17T02:34:27Z","abstract_excerpt":"Frame stacking is broadly applied in end-to-end neural network training like connectionist temporal classification (CTC), and it leads to more accurate models and faster decoding. However, it is not well-suited to conventional neural network based on context-dependent state acoustic model, if the decoder is unchanged. In this paper, we propose a novel frame retaining method which is applied in decoding. The system which combined frame retaining with frame stacking could reduces the time consumption of both training and decoding. Long short-term memory (LSTM) recurrent neural networks (RNNs) us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.05992","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":"1705.05992","created_at":"2026-05-18T00:44:19.267133+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.05992v1","created_at":"2026-05-18T00:44:19.267133+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.05992","created_at":"2026-05-18T00:44:19.267133+00:00"},{"alias_kind":"pith_short_12","alias_value":"YNICFBLWSL34","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_16","alias_value":"YNICFBLWSL34HBR3","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_8","alias_value":"YNICFBLW","created_at":"2026-05-18T12:31:56.362134+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/YNICFBLWSL34HBR325PSGLDKWR","json":"https://pith.science/pith/YNICFBLWSL34HBR325PSGLDKWR.json","graph_json":"https://pith.science/api/pith-number/YNICFBLWSL34HBR325PSGLDKWR/graph.json","events_json":"https://pith.science/api/pith-number/YNICFBLWSL34HBR325PSGLDKWR/events.json","paper":"https://pith.science/paper/YNICFBLW"},"agent_actions":{"view_html":"https://pith.science/pith/YNICFBLWSL34HBR325PSGLDKWR","download_json":"https://pith.science/pith/YNICFBLWSL34HBR325PSGLDKWR.json","view_paper":"https://pith.science/paper/YNICFBLW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.05992&json=true","fetch_graph":"https://pith.science/api/pith-number/YNICFBLWSL34HBR325PSGLDKWR/graph.json","fetch_events":"https://pith.science/api/pith-number/YNICFBLWSL34HBR325PSGLDKWR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YNICFBLWSL34HBR325PSGLDKWR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YNICFBLWSL34HBR325PSGLDKWR/action/storage_attestation","attest_author":"https://pith.science/pith/YNICFBLWSL34HBR325PSGLDKWR/action/author_attestation","sign_citation":"https://pith.science/pith/YNICFBLWSL34HBR325PSGLDKWR/action/citation_signature","submit_replication":"https://pith.science/pith/YNICFBLWSL34HBR325PSGLDKWR/action/replication_record"}},"created_at":"2026-05-18T00:44:19.267133+00:00","updated_at":"2026-05-18T00:44:19.267133+00:00"}