{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DYWIADMLAEN2R5YC5QPHTFSA47","short_pith_number":"pith:DYWIADML","schema_version":"1.0","canonical_sha256":"1e2c800d8b011ba8f702ec1e799640e7c41aab2a472c12350bf2c0d42e6a37a7","source":{"kind":"arxiv","id":"2305.15905","version":3},"attestation_state":"computed","paper":{"title":"Latent Diffusion Model Based Foley Sound Generation System For DCASE Challenge 2023 Task 7","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Haohe Liu, Mark D. Plumbley, Wenwu Wang, Xiyuan Kang, Xubo Liu, Yi Yuan","submitted_at":"2023-05-25T10:12:46Z","abstract_excerpt":"Foley sound presents the background sound for multimedia content and the generation of Foley sound involves computationally modelling sound effects with specialized techniques. In this work, we proposed a system for DCASE 2023 challenge task 7: Foley Sound Synthesis. The proposed system is based on AudioLDM, which is a diffusion-based text-to-audio generation model. To alleviate the data-hungry problem, the system first trained with large-scale datasets and then downstreamed into this DCASE task via transfer learning. Through experiments, we found out that the feature extracted by the encoder "},"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":"2305.15905","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-25T10:12:46Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"2652aa3765842808d47f4a6c7eb23adcf325a8ce2ac8d5f47ecd4470e04a4e8c","abstract_canon_sha256":"21afd86c97dc5c64d6fdf2bc14b6424db7f33f7b131562f4b1289009d763ad92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:55.506997Z","signature_b64":"RfO1trHK/1X2uaWzLTt0xJC+3IUpD+knbfthj9nIJkwAay3F0+mgP13T0Z7NqjNTMYWLJNVyd3iQLbN/6P3eAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e2c800d8b011ba8f702ec1e799640e7c41aab2a472c12350bf2c0d42e6a37a7","last_reissued_at":"2026-07-05T06:50:55.506512Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:55.506512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Diffusion Model Based Foley Sound Generation System For DCASE Challenge 2023 Task 7","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Haohe Liu, Mark D. Plumbley, Wenwu Wang, Xiyuan Kang, Xubo Liu, Yi Yuan","submitted_at":"2023-05-25T10:12:46Z","abstract_excerpt":"Foley sound presents the background sound for multimedia content and the generation of Foley sound involves computationally modelling sound effects with specialized techniques. In this work, we proposed a system for DCASE 2023 challenge task 7: Foley Sound Synthesis. The proposed system is based on AudioLDM, which is a diffusion-based text-to-audio generation model. To alleviate the data-hungry problem, the system first trained with large-scale datasets and then downstreamed into this DCASE task via transfer learning. Through experiments, we found out that the feature extracted by the encoder "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15905","kind":"arxiv","version":3},"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/2305.15905/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":"2305.15905","created_at":"2026-07-05T06:50:55.506574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15905v3","created_at":"2026-07-05T06:50:55.506574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15905","created_at":"2026-07-05T06:50:55.506574+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYWIADMLAEN2","created_at":"2026-07-05T06:50:55.506574+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYWIADMLAEN2R5YC","created_at":"2026-07-05T06:50:55.506574+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYWIADML","created_at":"2026-07-05T06:50:55.506574+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/DYWIADMLAEN2R5YC5QPHTFSA47","json":"https://pith.science/pith/DYWIADMLAEN2R5YC5QPHTFSA47.json","graph_json":"https://pith.science/api/pith-number/DYWIADMLAEN2R5YC5QPHTFSA47/graph.json","events_json":"https://pith.science/api/pith-number/DYWIADMLAEN2R5YC5QPHTFSA47/events.json","paper":"https://pith.science/paper/DYWIADML"},"agent_actions":{"view_html":"https://pith.science/pith/DYWIADMLAEN2R5YC5QPHTFSA47","download_json":"https://pith.science/pith/DYWIADMLAEN2R5YC5QPHTFSA47.json","view_paper":"https://pith.science/paper/DYWIADML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15905&json=true","fetch_graph":"https://pith.science/api/pith-number/DYWIADMLAEN2R5YC5QPHTFSA47/graph.json","fetch_events":"https://pith.science/api/pith-number/DYWIADMLAEN2R5YC5QPHTFSA47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYWIADMLAEN2R5YC5QPHTFSA47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYWIADMLAEN2R5YC5QPHTFSA47/action/storage_attestation","attest_author":"https://pith.science/pith/DYWIADMLAEN2R5YC5QPHTFSA47/action/author_attestation","sign_citation":"https://pith.science/pith/DYWIADMLAEN2R5YC5QPHTFSA47/action/citation_signature","submit_replication":"https://pith.science/pith/DYWIADMLAEN2R5YC5QPHTFSA47/action/replication_record"}},"created_at":"2026-07-05T06:50:55.506574+00:00","updated_at":"2026-07-05T06:50:55.506574+00:00"}