{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:SWUHPNTJE2JM6UTMFEJMQNGK3U","short_pith_number":"pith:SWUHPNTJ","schema_version":"1.0","canonical_sha256":"95a877b6692692cf526c2912c834cadd0e261a5989583ffecd09c62c9d8d677d","source":{"kind":"arxiv","id":"1610.05812","version":4},"attestation_state":"computed","paper":{"title":"Small-footprint Highway Deep Neural Networks for Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Liang Lu, Steve Renals","submitted_at":"2016-10-18T22:06:01Z","abstract_excerpt":"State-of-the-art speech recognition systems typically employ neural network acoustic models. However, compared to Gaussian mixture models, deep neural network (DNN) based acoustic models often have many more model parameters, making it challenging for them to be deployed on resource-constrained platforms, such as mobile devices. In this paper, we study the application of the recently proposed highway deep neural network (HDNN) for training small-footprint acoustic models. HDNNs are a depth-gated feedforward neural network, which include two types of gate functions to facilitate the information"},"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":"1610.05812","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-10-18T22:06:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0c73e230ee51641d549e38ffd37dd1bcabae0934cd9da62f68577cee88e49f0a","abstract_canon_sha256":"732bbf578e0e414a38f8602f54ce622e0aa7879d9a05d82ca33c6992fac7906f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:32.294132Z","signature_b64":"wsnLmC1Yfj1p3I4FNSC5pxrvQMXKBYJJppZ0X5P1GisE7ZnXfswkoQiSbWTFDIjPVGPOGWUG1YLiho5rouZbAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95a877b6692692cf526c2912c834cadd0e261a5989583ffecd09c62c9d8d677d","last_reissued_at":"2026-05-18T00:45:32.293699Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:32.293699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Small-footprint Highway Deep Neural Networks for Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Liang Lu, Steve Renals","submitted_at":"2016-10-18T22:06:01Z","abstract_excerpt":"State-of-the-art speech recognition systems typically employ neural network acoustic models. However, compared to Gaussian mixture models, deep neural network (DNN) based acoustic models often have many more model parameters, making it challenging for them to be deployed on resource-constrained platforms, such as mobile devices. In this paper, we study the application of the recently proposed highway deep neural network (HDNN) for training small-footprint acoustic models. HDNNs are a depth-gated feedforward neural network, which include two types of gate functions to facilitate the information"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.05812","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":""},"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":"1610.05812","created_at":"2026-05-18T00:45:32.293779+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.05812v4","created_at":"2026-05-18T00:45:32.293779+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.05812","created_at":"2026-05-18T00:45:32.293779+00:00"},{"alias_kind":"pith_short_12","alias_value":"SWUHPNTJE2JM","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_16","alias_value":"SWUHPNTJE2JM6UTM","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_8","alias_value":"SWUHPNTJ","created_at":"2026-05-18T12:30:44.179134+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/SWUHPNTJE2JM6UTMFEJMQNGK3U","json":"https://pith.science/pith/SWUHPNTJE2JM6UTMFEJMQNGK3U.json","graph_json":"https://pith.science/api/pith-number/SWUHPNTJE2JM6UTMFEJMQNGK3U/graph.json","events_json":"https://pith.science/api/pith-number/SWUHPNTJE2JM6UTMFEJMQNGK3U/events.json","paper":"https://pith.science/paper/SWUHPNTJ"},"agent_actions":{"view_html":"https://pith.science/pith/SWUHPNTJE2JM6UTMFEJMQNGK3U","download_json":"https://pith.science/pith/SWUHPNTJE2JM6UTMFEJMQNGK3U.json","view_paper":"https://pith.science/paper/SWUHPNTJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.05812&json=true","fetch_graph":"https://pith.science/api/pith-number/SWUHPNTJE2JM6UTMFEJMQNGK3U/graph.json","fetch_events":"https://pith.science/api/pith-number/SWUHPNTJE2JM6UTMFEJMQNGK3U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SWUHPNTJE2JM6UTMFEJMQNGK3U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SWUHPNTJE2JM6UTMFEJMQNGK3U/action/storage_attestation","attest_author":"https://pith.science/pith/SWUHPNTJE2JM6UTMFEJMQNGK3U/action/author_attestation","sign_citation":"https://pith.science/pith/SWUHPNTJE2JM6UTMFEJMQNGK3U/action/citation_signature","submit_replication":"https://pith.science/pith/SWUHPNTJE2JM6UTMFEJMQNGK3U/action/replication_record"}},"created_at":"2026-05-18T00:45:32.293779+00:00","updated_at":"2026-05-18T00:45:32.293779+00:00"}