{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UHEEB4IZS7WY4YRRBAFLGDPWZI","short_pith_number":"pith:UHEEB4IZ","schema_version":"1.0","canonical_sha256":"a1c840f11997ed8e6231080ab30df6ca2d8b4123e96e1d828d109e59201f473f","source":{"kind":"arxiv","id":"1808.08929","version":1},"attestation_state":"computed","paper":{"title":"A neural attention model for speech command recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Christoph Bernkopf, Douglas Coimbra de Andrade, Martin Loesener Da Silva Viana, Sabato Leo","submitted_at":"2018-08-27T17:05:50Z","abstract_excerpt":"This paper introduces a convolutional recurrent network with attention for speech command recognition. Attention models are powerful tools to improve performance on natural language, image captioning and speech tasks. The proposed model establishes a new state-of-the-art accuracy of 94.1% on Google Speech Commands dataset V1 and 94.5% on V2 (for the 20-commands recognition task), while still keeping a small footprint of only 202K trainable parameters. Results are compared with previous convolutional implementations on 5 different tasks (20 commands recognition (V1 and V2), 12 commands recognit"},"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":"1808.08929","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2018-08-27T17:05:50Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"fde729909e31643970d048e43b6e30adac35e57e63a4de584fa721b615d7c976","abstract_canon_sha256":"793d1ecbfcc2d13d590357080d2bd3caef2c4d2db4f98ceaf6ec5cad02fb94b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:12.791041Z","signature_b64":"v2kJllNZ67NflRL9F09g21nIAcAJtlLJYOGCrtOnOtUuQ2gB628hq0jGHBIrU+9P16K+e8RyF5XunX+49ZG+Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1c840f11997ed8e6231080ab30df6ca2d8b4123e96e1d828d109e59201f473f","last_reissued_at":"2026-05-18T00:07:12.790496Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:12.790496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A neural attention model for speech command recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Christoph Bernkopf, Douglas Coimbra de Andrade, Martin Loesener Da Silva Viana, Sabato Leo","submitted_at":"2018-08-27T17:05:50Z","abstract_excerpt":"This paper introduces a convolutional recurrent network with attention for speech command recognition. Attention models are powerful tools to improve performance on natural language, image captioning and speech tasks. The proposed model establishes a new state-of-the-art accuracy of 94.1% on Google Speech Commands dataset V1 and 94.5% on V2 (for the 20-commands recognition task), while still keeping a small footprint of only 202K trainable parameters. Results are compared with previous convolutional implementations on 5 different tasks (20 commands recognition (V1 and V2), 12 commands recognit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.08929","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":"1808.08929","created_at":"2026-05-18T00:07:12.790574+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.08929v1","created_at":"2026-05-18T00:07:12.790574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.08929","created_at":"2026-05-18T00:07:12.790574+00:00"},{"alias_kind":"pith_short_12","alias_value":"UHEEB4IZS7WY","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"UHEEB4IZS7WY4YRR","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"UHEEB4IZ","created_at":"2026-05-18T12:32:56.356000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.04536","citing_title":"Multi-layer Attention Mechanism for Speech Keyword Recognition","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UHEEB4IZS7WY4YRRBAFLGDPWZI","json":"https://pith.science/pith/UHEEB4IZS7WY4YRRBAFLGDPWZI.json","graph_json":"https://pith.science/api/pith-number/UHEEB4IZS7WY4YRRBAFLGDPWZI/graph.json","events_json":"https://pith.science/api/pith-number/UHEEB4IZS7WY4YRRBAFLGDPWZI/events.json","paper":"https://pith.science/paper/UHEEB4IZ"},"agent_actions":{"view_html":"https://pith.science/pith/UHEEB4IZS7WY4YRRBAFLGDPWZI","download_json":"https://pith.science/pith/UHEEB4IZS7WY4YRRBAFLGDPWZI.json","view_paper":"https://pith.science/paper/UHEEB4IZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.08929&json=true","fetch_graph":"https://pith.science/api/pith-number/UHEEB4IZS7WY4YRRBAFLGDPWZI/graph.json","fetch_events":"https://pith.science/api/pith-number/UHEEB4IZS7WY4YRRBAFLGDPWZI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UHEEB4IZS7WY4YRRBAFLGDPWZI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UHEEB4IZS7WY4YRRBAFLGDPWZI/action/storage_attestation","attest_author":"https://pith.science/pith/UHEEB4IZS7WY4YRRBAFLGDPWZI/action/author_attestation","sign_citation":"https://pith.science/pith/UHEEB4IZS7WY4YRRBAFLGDPWZI/action/citation_signature","submit_replication":"https://pith.science/pith/UHEEB4IZS7WY4YRRBAFLGDPWZI/action/replication_record"}},"created_at":"2026-05-18T00:07:12.790574+00:00","updated_at":"2026-05-18T00:07:12.790574+00:00"}