{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TZB7LQPQQ46PUT6BJOEFM2YSKA","short_pith_number":"pith:TZB7LQPQ","schema_version":"1.0","canonical_sha256":"9e43f5c1f0873cfa4fc14b88566b12503b5f1826e2c2d4e867453d9cd3d824c5","source":{"kind":"arxiv","id":"1911.02115","version":2},"attestation_state":"computed","paper":{"title":"Spatial Attention for Far-field Speech Recognition with Deep Beamforming Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Biqiao Zhang, Christian Fuegen, Jay Mahadeokar, Kaustubh Kalgaonkar, Lu Lu, Weipeng He","submitted_at":"2019-11-05T22:40:45Z","abstract_excerpt":"In this paper, we introduce spatial attention for refining the information in multi-direction neural beamformer for far-field automatic speech recognition. Previous approaches of neural beamformers with multiple look directions, such as the factored complex linear projection, have shown promising results. However, the features extracted by such methods contain redundant information, as only the direction of the target speech is relevant. We propose using a spatial attention subnet to weigh the features from different directions, so that the subsequent acoustic model could focus on the most rel"},"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":"1911.02115","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-11-05T22:40:45Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"1af45b848ba707c5ae775faeca450bc37b07e6b14d03771c61593873a427a238","abstract_canon_sha256":"891f15ef3df2db8d3c75b62c93aa7cf2fc41eaeab809070a5f8bcd5b7bfbbd6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:46:33.305219Z","signature_b64":"2g//xzgDStHxD+8neduXPG9sQ0045SeJ4BTvpAkYTUnjy/Wpj0WRHYtGBwSkdBACGaG4/0iFx+TifhmlRi5IDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e43f5c1f0873cfa4fc14b88566b12503b5f1826e2c2d4e867453d9cd3d824c5","last_reissued_at":"2026-07-05T00:46:33.304822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:46:33.304822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatial Attention for Far-field Speech Recognition with Deep Beamforming Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Biqiao Zhang, Christian Fuegen, Jay Mahadeokar, Kaustubh Kalgaonkar, Lu Lu, Weipeng He","submitted_at":"2019-11-05T22:40:45Z","abstract_excerpt":"In this paper, we introduce spatial attention for refining the information in multi-direction neural beamformer for far-field automatic speech recognition. Previous approaches of neural beamformers with multiple look directions, such as the factored complex linear projection, have shown promising results. However, the features extracted by such methods contain redundant information, as only the direction of the target speech is relevant. We propose using a spatial attention subnet to weigh the features from different directions, so that the subsequent acoustic model could focus on the most rel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.02115","kind":"arxiv","version":2},"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/1911.02115/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":"1911.02115","created_at":"2026-07-05T00:46:33.304878+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.02115v2","created_at":"2026-07-05T00:46:33.304878+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.02115","created_at":"2026-07-05T00:46:33.304878+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZB7LQPQQ46P","created_at":"2026-07-05T00:46:33.304878+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZB7LQPQQ46PUT6B","created_at":"2026-07-05T00:46:33.304878+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZB7LQPQ","created_at":"2026-07-05T00:46:33.304878+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/TZB7LQPQQ46PUT6BJOEFM2YSKA","json":"https://pith.science/pith/TZB7LQPQQ46PUT6BJOEFM2YSKA.json","graph_json":"https://pith.science/api/pith-number/TZB7LQPQQ46PUT6BJOEFM2YSKA/graph.json","events_json":"https://pith.science/api/pith-number/TZB7LQPQQ46PUT6BJOEFM2YSKA/events.json","paper":"https://pith.science/paper/TZB7LQPQ"},"agent_actions":{"view_html":"https://pith.science/pith/TZB7LQPQQ46PUT6BJOEFM2YSKA","download_json":"https://pith.science/pith/TZB7LQPQQ46PUT6BJOEFM2YSKA.json","view_paper":"https://pith.science/paper/TZB7LQPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.02115&json=true","fetch_graph":"https://pith.science/api/pith-number/TZB7LQPQQ46PUT6BJOEFM2YSKA/graph.json","fetch_events":"https://pith.science/api/pith-number/TZB7LQPQQ46PUT6BJOEFM2YSKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZB7LQPQQ46PUT6BJOEFM2YSKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZB7LQPQQ46PUT6BJOEFM2YSKA/action/storage_attestation","attest_author":"https://pith.science/pith/TZB7LQPQQ46PUT6BJOEFM2YSKA/action/author_attestation","sign_citation":"https://pith.science/pith/TZB7LQPQQ46PUT6BJOEFM2YSKA/action/citation_signature","submit_replication":"https://pith.science/pith/TZB7LQPQQ46PUT6BJOEFM2YSKA/action/replication_record"}},"created_at":"2026-07-05T00:46:33.304878+00:00","updated_at":"2026-07-05T00:46:33.304878+00:00"}