{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PAXP5RDPNDM2KDDAVSLCIGKMKO","short_pith_number":"pith:PAXP5RDP","schema_version":"1.0","canonical_sha256":"782efec46f68d9a50c60ac9624194c53bf6e5fc0ff7094aa42d372a2305baa41","source":{"kind":"arxiv","id":"2407.04879","version":1},"attestation_state":"computed","paper":{"title":"All Neural Low-latency Directional Speech Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Ashutosh Pandey, Buye Xu, Daniel Wong, Juan Azcarreta, Sanha Lee","submitted_at":"2024-07-05T22:17:11Z","abstract_excerpt":"We introduce a novel all neural model for low-latency directional speech extraction. The model uses direction of arrival (DOA) embeddings from a predefined spatial grid, which are transformed and fused into a recurrent neural network based speech extraction model. This process enables the model to effectively extract speech from a specified DOA. Unlike previous methods that relied on hand-crafted directional features, the proposed model trains DOA embeddings from scratch using speech enhancement loss, making it suitable for low-latency scenarios. Additionally, it operates at a high frame rate,"},"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":"2407.04879","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-05T22:17:11Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"4a1237b690b6fdacb22b2d046b0a70720295c0ce136b56c50d497c79387d1fe0","abstract_canon_sha256":"1855be0e88ef97995e84275e9555c1d3884acd0418ada90f4eb00382cc29b10b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:43.134547Z","signature_b64":"E5EalYE/3jtnHCNnAwgPscUejSv87Pq++qFXD6ph3enXuOPjNH345lXZkoNYUvzQGJzwFdnf/tUuoJ/sFLRxBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"782efec46f68d9a50c60ac9624194c53bf6e5fc0ff7094aa42d372a2305baa41","last_reissued_at":"2026-07-05T08:40:43.134020Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:43.134020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"All Neural Low-latency Directional Speech Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Ashutosh Pandey, Buye Xu, Daniel Wong, Juan Azcarreta, Sanha Lee","submitted_at":"2024-07-05T22:17:11Z","abstract_excerpt":"We introduce a novel all neural model for low-latency directional speech extraction. The model uses direction of arrival (DOA) embeddings from a predefined spatial grid, which are transformed and fused into a recurrent neural network based speech extraction model. This process enables the model to effectively extract speech from a specified DOA. Unlike previous methods that relied on hand-crafted directional features, the proposed model trains DOA embeddings from scratch using speech enhancement loss, making it suitable for low-latency scenarios. Additionally, it operates at a high frame rate,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04879","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.04879/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":"2407.04879","created_at":"2026-07-05T08:40:43.134076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.04879v1","created_at":"2026-07-05T08:40:43.134076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04879","created_at":"2026-07-05T08:40:43.134076+00:00"},{"alias_kind":"pith_short_12","alias_value":"PAXP5RDPNDM2","created_at":"2026-07-05T08:40:43.134076+00:00"},{"alias_kind":"pith_short_16","alias_value":"PAXP5RDPNDM2KDDA","created_at":"2026-07-05T08:40:43.134076+00:00"},{"alias_kind":"pith_short_8","alias_value":"PAXP5RDP","created_at":"2026-07-05T08:40:43.134076+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02296","citing_title":"Spatial Speech Perception Systems: A Survey of Sound Source Localization, Directional Enhancement, and Speech Recognition","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PAXP5RDPNDM2KDDAVSLCIGKMKO","json":"https://pith.science/pith/PAXP5RDPNDM2KDDAVSLCIGKMKO.json","graph_json":"https://pith.science/api/pith-number/PAXP5RDPNDM2KDDAVSLCIGKMKO/graph.json","events_json":"https://pith.science/api/pith-number/PAXP5RDPNDM2KDDAVSLCIGKMKO/events.json","paper":"https://pith.science/paper/PAXP5RDP"},"agent_actions":{"view_html":"https://pith.science/pith/PAXP5RDPNDM2KDDAVSLCIGKMKO","download_json":"https://pith.science/pith/PAXP5RDPNDM2KDDAVSLCIGKMKO.json","view_paper":"https://pith.science/paper/PAXP5RDP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.04879&json=true","fetch_graph":"https://pith.science/api/pith-number/PAXP5RDPNDM2KDDAVSLCIGKMKO/graph.json","fetch_events":"https://pith.science/api/pith-number/PAXP5RDPNDM2KDDAVSLCIGKMKO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PAXP5RDPNDM2KDDAVSLCIGKMKO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PAXP5RDPNDM2KDDAVSLCIGKMKO/action/storage_attestation","attest_author":"https://pith.science/pith/PAXP5RDPNDM2KDDAVSLCIGKMKO/action/author_attestation","sign_citation":"https://pith.science/pith/PAXP5RDPNDM2KDDAVSLCIGKMKO/action/citation_signature","submit_replication":"https://pith.science/pith/PAXP5RDPNDM2KDDAVSLCIGKMKO/action/replication_record"}},"created_at":"2026-07-05T08:40:43.134076+00:00","updated_at":"2026-07-05T08:40:43.134076+00:00"}