{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VUTG6WJ5JS4MK2AHM4GBS4QWC5","short_pith_number":"pith:VUTG6WJ5","schema_version":"1.0","canonical_sha256":"ad266f593d4cb8c56807670c1972161778bd81384e37ab5bfd73d263f0fd061b","source":{"kind":"arxiv","id":"2605.14736","version":1},"attestation_state":"computed","paper":{"title":"IsoNet: Spatially-aware audio-visual target speech extraction in complex acoustic environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SD","authors_text":"Binita Adhikari, Dinanath Pathya, Ishwor Raj Pokharel, Sajen Maharjan","submitted_at":"2026-05-14T12:00:13Z","abstract_excerpt":"Target speech extraction remains difficult for compact devices because monaural neural models lack spatial evidence and classical beamformers lose resolving power when the microphone aperture is only a few centimetres. We present IsoNet, a user-selectable audio-visual target speech extraction system for a compact 4-microphone array. IsoNet combines complex multi-channel STFT features, GCC-PHAT spatial cues, face-conditioned visual embeddings, and auxiliary direction-of-arrival supervision inside a U-Net mask estimation network. Three curriculum variants were trained on 25,000 simulated VoxCele"},"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":"2605.14736","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-14T12:00:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e275329ac4e6cefd85f7a36dbccd8249a133636e295ea1749c48698f622a84ec","abstract_canon_sha256":"bb25066e81dfa97a23a2925bdbe8858bd548ac5126cb6def05d933f6547a4c0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:58.980056Z","signature_b64":"KUo//GwUDtKny/ZuhDsHWMeEt12CLC8rWYHHNSjfARrU3VYMhy4E3dZxWcn7Mia/JVcrOoh5tBvBKAOipl7SDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad266f593d4cb8c56807670c1972161778bd81384e37ab5bfd73d263f0fd061b","last_reissued_at":"2026-05-17T23:38:58.979465Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:58.979465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IsoNet: Spatially-aware audio-visual target speech extraction in complex acoustic environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SD","authors_text":"Binita Adhikari, Dinanath Pathya, Ishwor Raj Pokharel, Sajen Maharjan","submitted_at":"2026-05-14T12:00:13Z","abstract_excerpt":"Target speech extraction remains difficult for compact devices because monaural neural models lack spatial evidence and classical beamformers lose resolving power when the microphone aperture is only a few centimetres. We present IsoNet, a user-selectable audio-visual target speech extraction system for a compact 4-microphone array. IsoNet combines complex multi-channel STFT features, GCC-PHAT spatial cues, face-conditioned visual embeddings, and auxiliary direction-of-arrival supervision inside a U-Net mask estimation network. Three curriculum variants were trained on 25,000 simulated VoxCele"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14736","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":"2605.14736","created_at":"2026-05-17T23:38:58.979550+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14736v1","created_at":"2026-05-17T23:38:58.979550+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14736","created_at":"2026-05-17T23:38:58.979550+00:00"},{"alias_kind":"pith_short_12","alias_value":"VUTG6WJ5JS4M","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"VUTG6WJ5JS4MK2AH","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"VUTG6WJ5","created_at":"2026-05-18T12:33:37.589309+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/VUTG6WJ5JS4MK2AHM4GBS4QWC5","json":"https://pith.science/pith/VUTG6WJ5JS4MK2AHM4GBS4QWC5.json","graph_json":"https://pith.science/api/pith-number/VUTG6WJ5JS4MK2AHM4GBS4QWC5/graph.json","events_json":"https://pith.science/api/pith-number/VUTG6WJ5JS4MK2AHM4GBS4QWC5/events.json","paper":"https://pith.science/paper/VUTG6WJ5"},"agent_actions":{"view_html":"https://pith.science/pith/VUTG6WJ5JS4MK2AHM4GBS4QWC5","download_json":"https://pith.science/pith/VUTG6WJ5JS4MK2AHM4GBS4QWC5.json","view_paper":"https://pith.science/paper/VUTG6WJ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14736&json=true","fetch_graph":"https://pith.science/api/pith-number/VUTG6WJ5JS4MK2AHM4GBS4QWC5/graph.json","fetch_events":"https://pith.science/api/pith-number/VUTG6WJ5JS4MK2AHM4GBS4QWC5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VUTG6WJ5JS4MK2AHM4GBS4QWC5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VUTG6WJ5JS4MK2AHM4GBS4QWC5/action/storage_attestation","attest_author":"https://pith.science/pith/VUTG6WJ5JS4MK2AHM4GBS4QWC5/action/author_attestation","sign_citation":"https://pith.science/pith/VUTG6WJ5JS4MK2AHM4GBS4QWC5/action/citation_signature","submit_replication":"https://pith.science/pith/VUTG6WJ5JS4MK2AHM4GBS4QWC5/action/replication_record"}},"created_at":"2026-05-17T23:38:58.979550+00:00","updated_at":"2026-05-17T23:38:58.979550+00:00"}