{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ZLILAMSAJ4POFUP373JBOHZRMC","short_pith_number":"pith:ZLILAMSA","schema_version":"1.0","canonical_sha256":"cad0b032404f1ee2d1fbfed2171f316089bdb69f904e71e66b8ceff460f24ced","source":{"kind":"arxiv","id":"1705.02411","version":1},"attestation_state":"computed","paper":{"title":"Max-Pooling Loss Training of Long Short-Term Memory Networks for Small-Footprint Keyword Spotting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Anirudh Raju, Arindam Mandal, Gengshen Fu, George Tucker, Ming Sun, Nikko Strom, Sankaran Panchapagesan, Shiv Vitaladevuni, Spyros Matsoukas","submitted_at":"2017-05-05T22:36:04Z","abstract_excerpt":"We propose a max-pooling based loss function for training Long Short-Term Memory (LSTM) networks for small-footprint keyword spotting (KWS), with low CPU, memory, and latency requirements. The max-pooling loss training can be further guided by initializing with a cross-entropy loss trained network. A posterior smoothing based evaluation approach is employed to measure keyword spotting performance. Our experimental results show that LSTM models trained using cross-entropy loss or max-pooling loss outperform a cross-entropy loss trained baseline feed-forward Deep Neural Network (DNN). In additio"},"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":"1705.02411","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-05T22:36:04Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"507d8cb50d3e06c0c86ef33663c9f8a575fead1b0b65df2916c6509c6df86966","abstract_canon_sha256":"ca815ed58e028d7de845d17c1553962da4cfe9b7fe22a2ae0c5418f9b8dc90f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:56.652302Z","signature_b64":"nAzscycjOosyiKzTk31UCNQAnvSxWJxIwBPuDpq6ZhYTOqJTXgudsFWH8Rub3GLXT/4KCeKnLMAOwS1i82ntAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cad0b032404f1ee2d1fbfed2171f316089bdb69f904e71e66b8ceff460f24ced","last_reissued_at":"2026-05-18T00:44:56.651446Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:56.651446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Max-Pooling Loss Training of Long Short-Term Memory Networks for Small-Footprint Keyword Spotting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Anirudh Raju, Arindam Mandal, Gengshen Fu, George Tucker, Ming Sun, Nikko Strom, Sankaran Panchapagesan, Shiv Vitaladevuni, Spyros Matsoukas","submitted_at":"2017-05-05T22:36:04Z","abstract_excerpt":"We propose a max-pooling based loss function for training Long Short-Term Memory (LSTM) networks for small-footprint keyword spotting (KWS), with low CPU, memory, and latency requirements. The max-pooling loss training can be further guided by initializing with a cross-entropy loss trained network. A posterior smoothing based evaluation approach is employed to measure keyword spotting performance. Our experimental results show that LSTM models trained using cross-entropy loss or max-pooling loss outperform a cross-entropy loss trained baseline feed-forward Deep Neural Network (DNN). In additio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.02411","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":"1705.02411","created_at":"2026-05-18T00:44:56.651599+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.02411v1","created_at":"2026-05-18T00:44:56.651599+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.02411","created_at":"2026-05-18T00:44:56.651599+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZLILAMSAJ4PO","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZLILAMSAJ4POFUP3","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZLILAMSA","created_at":"2026-05-18T12:31:59.375834+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/ZLILAMSAJ4POFUP373JBOHZRMC","json":"https://pith.science/pith/ZLILAMSAJ4POFUP373JBOHZRMC.json","graph_json":"https://pith.science/api/pith-number/ZLILAMSAJ4POFUP373JBOHZRMC/graph.json","events_json":"https://pith.science/api/pith-number/ZLILAMSAJ4POFUP373JBOHZRMC/events.json","paper":"https://pith.science/paper/ZLILAMSA"},"agent_actions":{"view_html":"https://pith.science/pith/ZLILAMSAJ4POFUP373JBOHZRMC","download_json":"https://pith.science/pith/ZLILAMSAJ4POFUP373JBOHZRMC.json","view_paper":"https://pith.science/paper/ZLILAMSA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.02411&json=true","fetch_graph":"https://pith.science/api/pith-number/ZLILAMSAJ4POFUP373JBOHZRMC/graph.json","fetch_events":"https://pith.science/api/pith-number/ZLILAMSAJ4POFUP373JBOHZRMC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZLILAMSAJ4POFUP373JBOHZRMC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZLILAMSAJ4POFUP373JBOHZRMC/action/storage_attestation","attest_author":"https://pith.science/pith/ZLILAMSAJ4POFUP373JBOHZRMC/action/author_attestation","sign_citation":"https://pith.science/pith/ZLILAMSAJ4POFUP373JBOHZRMC/action/citation_signature","submit_replication":"https://pith.science/pith/ZLILAMSAJ4POFUP373JBOHZRMC/action/replication_record"}},"created_at":"2026-05-18T00:44:56.651599+00:00","updated_at":"2026-05-18T00:44:56.651599+00:00"}