{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:AU5C7EWUOKJSFLCPDLX66H6SPA","short_pith_number":"pith:AU5C7EWU","schema_version":"1.0","canonical_sha256":"053a2f92d4729322ac4f1aefef1fd2782c3b0da540bc64d7e051dfeda3c3bbca","source":{"kind":"arxiv","id":"2007.08818","version":4},"attestation_state":"computed","paper":{"title":"Neural Architecture Search For LF-MMI Trained Time Delay Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Helen Meng, Mengzhe Geng, Mingyu Cui, Shansong Liu, Shoukang Hu, Xunying Liu, Xurong Xie","submitted_at":"2020-07-17T08:32:11Z","abstract_excerpt":"Deep neural networks (DNNs) based automatic speech recognition (ASR) systems are often designed using expert knowledge and empirical evaluation. In this paper, a range of neural architecture search (NAS) techniques are used to automatically learn two types of hyper-parameters of state-of-the-art factored time delay neural networks (TDNNs): i) the left and right splicing context offsets; and ii) the dimensionality of the bottleneck linear projection at each hidden layer. These include the DARTS method integrating architecture selection with lattice-free MMI (LF-MMI) TDNN training; Gumbel-Softma"},"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":"2007.08818","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-07-17T08:32:11Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"d9f2f79c1d949c3f2483e1c7c752a875b5f0d327619307fc50903487e668d3da","abstract_canon_sha256":"86a387f53bc9f383051477166ca883ef4f5bb7e801e163da8143537e4b75a6e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:13:15.738738Z","signature_b64":"/2Hr5Nh1gQ7ZkcuKUNnuB/eI78tMAZT/r1C8hOI+gs1CgECnyFkelN5HrLgJra/0PaujZMHIda0cn/Q5R6ZQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"053a2f92d4729322ac4f1aefef1fd2782c3b0da540bc64d7e051dfeda3c3bbca","last_reissued_at":"2026-07-05T02:13:15.738175Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:13:15.738175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Architecture Search For LF-MMI Trained Time Delay Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Helen Meng, Mengzhe Geng, Mingyu Cui, Shansong Liu, Shoukang Hu, Xunying Liu, Xurong Xie","submitted_at":"2020-07-17T08:32:11Z","abstract_excerpt":"Deep neural networks (DNNs) based automatic speech recognition (ASR) systems are often designed using expert knowledge and empirical evaluation. In this paper, a range of neural architecture search (NAS) techniques are used to automatically learn two types of hyper-parameters of state-of-the-art factored time delay neural networks (TDNNs): i) the left and right splicing context offsets; and ii) the dimensionality of the bottleneck linear projection at each hidden layer. These include the DARTS method integrating architecture selection with lattice-free MMI (LF-MMI) TDNN training; Gumbel-Softma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.08818","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.08818/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2007.08818","created_at":"2026-07-05T02:13:15.738234+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.08818v4","created_at":"2026-07-05T02:13:15.738234+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.08818","created_at":"2026-07-05T02:13:15.738234+00:00"},{"alias_kind":"pith_short_12","alias_value":"AU5C7EWUOKJS","created_at":"2026-07-05T02:13:15.738234+00:00"},{"alias_kind":"pith_short_16","alias_value":"AU5C7EWUOKJSFLCP","created_at":"2026-07-05T02:13:15.738234+00:00"},{"alias_kind":"pith_short_8","alias_value":"AU5C7EWU","created_at":"2026-07-05T02:13:15.738234+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/AU5C7EWUOKJSFLCPDLX66H6SPA","json":"https://pith.science/pith/AU5C7EWUOKJSFLCPDLX66H6SPA.json","graph_json":"https://pith.science/api/pith-number/AU5C7EWUOKJSFLCPDLX66H6SPA/graph.json","events_json":"https://pith.science/api/pith-number/AU5C7EWUOKJSFLCPDLX66H6SPA/events.json","paper":"https://pith.science/paper/AU5C7EWU"},"agent_actions":{"view_html":"https://pith.science/pith/AU5C7EWUOKJSFLCPDLX66H6SPA","download_json":"https://pith.science/pith/AU5C7EWUOKJSFLCPDLX66H6SPA.json","view_paper":"https://pith.science/paper/AU5C7EWU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.08818&json=true","fetch_graph":"https://pith.science/api/pith-number/AU5C7EWUOKJSFLCPDLX66H6SPA/graph.json","fetch_events":"https://pith.science/api/pith-number/AU5C7EWUOKJSFLCPDLX66H6SPA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AU5C7EWUOKJSFLCPDLX66H6SPA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AU5C7EWUOKJSFLCPDLX66H6SPA/action/storage_attestation","attest_author":"https://pith.science/pith/AU5C7EWUOKJSFLCPDLX66H6SPA/action/author_attestation","sign_citation":"https://pith.science/pith/AU5C7EWUOKJSFLCPDLX66H6SPA/action/citation_signature","submit_replication":"https://pith.science/pith/AU5C7EWUOKJSFLCPDLX66H6SPA/action/replication_record"}},"created_at":"2026-07-05T02:13:15.738234+00:00","updated_at":"2026-07-05T02:13:15.738234+00:00"}