{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HHXYZSTGUFBGXCXIBCJCJUBKME","short_pith_number":"pith:HHXYZSTG","schema_version":"1.0","canonical_sha256":"39ef8cca66a1426b8ae8089224d02a61357997c6634dda1da66f1abb64a8a5d4","source":{"kind":"arxiv","id":"2502.11219","version":1},"attestation_state":"computed","paper":{"title":"AudioSpa: Spatializing Sound Events with Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Boyu Zhu, Lei Zhao, Linfeng Feng, Xiao-Lei Zhang, Xuelong Li","submitted_at":"2025-02-16T17:41:14Z","abstract_excerpt":"Text-to-audio (TTA) systems have recently demonstrated strong performance in synthesizing monaural audio from text. However, the task of generating binaural spatial audio from text, which provides a more immersive auditory experience by incorporating the sense of spatiality, have not been explored yet. In this work, we introduce text-guided binaural audio generation. As an early effort, we focus on the scenario where a monaural reference audio is given additionally. The core problem is to associate specific sound events with their directions, thereby creating binaural spatial audio. The challe"},"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":"2502.11219","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-02-16T17:41:14Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"a0d42e9af4b9c5c72b681c27bf72958d04f8c8e2cf7041071b7a6e2ca00c4495","abstract_canon_sha256":"fa5c641a0c5106f36f7af84a522b63e6bc417c7f37f33da17f50a5e9ad355eee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:05.243201Z","signature_b64":"B8kNhmwxLQY6G6yN52Tc93wKKx7m27smU3WE6K6clhTxaqJVyY+ICbDaRnT+0XWKvyWsmiZ4wKLVFT8Nqu2GAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39ef8cca66a1426b8ae8089224d02a61357997c6634dda1da66f1abb64a8a5d4","last_reissued_at":"2026-07-05T10:15:05.242717Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:05.242717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AudioSpa: Spatializing Sound Events with Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Boyu Zhu, Lei Zhao, Linfeng Feng, Xiao-Lei Zhang, Xuelong Li","submitted_at":"2025-02-16T17:41:14Z","abstract_excerpt":"Text-to-audio (TTA) systems have recently demonstrated strong performance in synthesizing monaural audio from text. However, the task of generating binaural spatial audio from text, which provides a more immersive auditory experience by incorporating the sense of spatiality, have not been explored yet. In this work, we introduce text-guided binaural audio generation. As an early effort, we focus on the scenario where a monaural reference audio is given additionally. The core problem is to associate specific sound events with their directions, thereby creating binaural spatial audio. The challe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11219","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/2502.11219/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":"2502.11219","created_at":"2026-07-05T10:15:05.242780+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.11219v1","created_at":"2026-07-05T10:15:05.242780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11219","created_at":"2026-07-05T10:15:05.242780+00:00"},{"alias_kind":"pith_short_12","alias_value":"HHXYZSTGUFBG","created_at":"2026-07-05T10:15:05.242780+00:00"},{"alias_kind":"pith_short_16","alias_value":"HHXYZSTGUFBGXCXI","created_at":"2026-07-05T10:15:05.242780+00:00"},{"alias_kind":"pith_short_8","alias_value":"HHXYZSTG","created_at":"2026-07-05T10:15:05.242780+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00400","citing_title":"Deep Learning for Personalized Binaural Audio Reproduction","ref_index":158,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HHXYZSTGUFBGXCXIBCJCJUBKME","json":"https://pith.science/pith/HHXYZSTGUFBGXCXIBCJCJUBKME.json","graph_json":"https://pith.science/api/pith-number/HHXYZSTGUFBGXCXIBCJCJUBKME/graph.json","events_json":"https://pith.science/api/pith-number/HHXYZSTGUFBGXCXIBCJCJUBKME/events.json","paper":"https://pith.science/paper/HHXYZSTG"},"agent_actions":{"view_html":"https://pith.science/pith/HHXYZSTGUFBGXCXIBCJCJUBKME","download_json":"https://pith.science/pith/HHXYZSTGUFBGXCXIBCJCJUBKME.json","view_paper":"https://pith.science/paper/HHXYZSTG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.11219&json=true","fetch_graph":"https://pith.science/api/pith-number/HHXYZSTGUFBGXCXIBCJCJUBKME/graph.json","fetch_events":"https://pith.science/api/pith-number/HHXYZSTGUFBGXCXIBCJCJUBKME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HHXYZSTGUFBGXCXIBCJCJUBKME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HHXYZSTGUFBGXCXIBCJCJUBKME/action/storage_attestation","attest_author":"https://pith.science/pith/HHXYZSTGUFBGXCXIBCJCJUBKME/action/author_attestation","sign_citation":"https://pith.science/pith/HHXYZSTGUFBGXCXIBCJCJUBKME/action/citation_signature","submit_replication":"https://pith.science/pith/HHXYZSTGUFBGXCXIBCJCJUBKME/action/replication_record"}},"created_at":"2026-07-05T10:15:05.242780+00:00","updated_at":"2026-07-05T10:15:05.242780+00:00"}