{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5RHHK5P3D2P6DODYUHRYRCNTGR","short_pith_number":"pith:5RHHK5P3","schema_version":"1.0","canonical_sha256":"ec4e7575fb1e9fe1b878a1e38889b3344d4f2d78a94400a7932ce030052b2278","source":{"kind":"arxiv","id":"2502.07538","version":2},"attestation_state":"computed","paper":{"title":"Visual-based spatial audio generation system for multi-speaker environments","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Joshua Reiss, Ogulcan Gurelli, Xiaojing Liu, Yan Wang","submitted_at":"2025-02-11T13:24:38Z","abstract_excerpt":"In multimedia applications such as films and video games, spatial audio techniques are widely employed to enhance user experiences by simulating 3D sound: transforming mono audio into binaural formats. However, this process is often complex and labor-intensive for sound designers, requiring precise synchronization of audio with the spatial positions of visual components. To address these challenges, we propose a visual-based spatial audio generation system - an automated system that integrates face detection YOLOv8 for object detection, monocular depth estimation, and spatial audio techniques."},"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":"2502.07538","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2025-02-11T13:24:38Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"761cb2ee34aa748a88bff4654c1fc4a4b11aa2587ca64aafe85297f2ef6e9055","abstract_canon_sha256":"44875c8da23c696b545b31cf495c5c0a3e8cdc0050bd8bda5b7cd17be3710478"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:48.316445Z","signature_b64":"xNBCHriN1ZsLsiMXx2NH9zJIcEacqTuvE2uX5OKSQ1CSw8TQiMJsSCX7RiVAOxOX+O0I6Onzv1VreRwdvuBcDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec4e7575fb1e9fe1b878a1e38889b3344d4f2d78a94400a7932ce030052b2278","last_reissued_at":"2026-07-05T10:13:48.315839Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:48.315839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual-based spatial audio generation system for multi-speaker environments","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Joshua Reiss, Ogulcan Gurelli, Xiaojing Liu, Yan Wang","submitted_at":"2025-02-11T13:24:38Z","abstract_excerpt":"In multimedia applications such as films and video games, spatial audio techniques are widely employed to enhance user experiences by simulating 3D sound: transforming mono audio into binaural formats. However, this process is often complex and labor-intensive for sound designers, requiring precise synchronization of audio with the spatial positions of visual components. To address these challenges, we propose a visual-based spatial audio generation system - an automated system that integrates face detection YOLOv8 for object detection, monocular depth estimation, and spatial audio techniques."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07538","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/2502.07538/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":"2502.07538","created_at":"2026-07-05T10:13:48.315902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.07538v2","created_at":"2026-07-05T10:13:48.315902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07538","created_at":"2026-07-05T10:13:48.315902+00:00"},{"alias_kind":"pith_short_12","alias_value":"5RHHK5P3D2P6","created_at":"2026-07-05T10:13:48.315902+00:00"},{"alias_kind":"pith_short_16","alias_value":"5RHHK5P3D2P6DODY","created_at":"2026-07-05T10:13:48.315902+00:00"},{"alias_kind":"pith_short_8","alias_value":"5RHHK5P3","created_at":"2026-07-05T10:13:48.315902+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10924","citing_title":"ASAudio: A Survey of Advanced Spatial Audio Research","ref_index":102,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5RHHK5P3D2P6DODYUHRYRCNTGR","json":"https://pith.science/pith/5RHHK5P3D2P6DODYUHRYRCNTGR.json","graph_json":"https://pith.science/api/pith-number/5RHHK5P3D2P6DODYUHRYRCNTGR/graph.json","events_json":"https://pith.science/api/pith-number/5RHHK5P3D2P6DODYUHRYRCNTGR/events.json","paper":"https://pith.science/paper/5RHHK5P3"},"agent_actions":{"view_html":"https://pith.science/pith/5RHHK5P3D2P6DODYUHRYRCNTGR","download_json":"https://pith.science/pith/5RHHK5P3D2P6DODYUHRYRCNTGR.json","view_paper":"https://pith.science/paper/5RHHK5P3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.07538&json=true","fetch_graph":"https://pith.science/api/pith-number/5RHHK5P3D2P6DODYUHRYRCNTGR/graph.json","fetch_events":"https://pith.science/api/pith-number/5RHHK5P3D2P6DODYUHRYRCNTGR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5RHHK5P3D2P6DODYUHRYRCNTGR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5RHHK5P3D2P6DODYUHRYRCNTGR/action/storage_attestation","attest_author":"https://pith.science/pith/5RHHK5P3D2P6DODYUHRYRCNTGR/action/author_attestation","sign_citation":"https://pith.science/pith/5RHHK5P3D2P6DODYUHRYRCNTGR/action/citation_signature","submit_replication":"https://pith.science/pith/5RHHK5P3D2P6DODYUHRYRCNTGR/action/replication_record"}},"created_at":"2026-07-05T10:13:48.315902+00:00","updated_at":"2026-07-05T10:13:48.315902+00:00"}