{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:366TMUZ7E3NMNT2KT3EQNIUBDB","short_pith_number":"pith:366TMUZ7","schema_version":"1.0","canonical_sha256":"dfbd36533f26dac6cf4a9ec906a2811849d42afce92269e129c5721efa1bcadf","source":{"kind":"arxiv","id":"2306.09807","version":2},"attestation_state":"computed","paper":{"title":"FALL-E: A Foley Sound Synthesis Model and Strategies","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ben Sangbae Chon, Hyeongi Moon, Kyungyun Lee, Minsung Kang, Sangshin Oh","submitted_at":"2023-06-16T12:44:10Z","abstract_excerpt":"This paper introduces FALL-E, a foley synthesis system and its training/inference strategies. The FALL-E model employs a cascaded approach comprising low-resolution spectrogram generation, spectrogram super-resolution, and a vocoder. We trained every sound-related model from scratch using our extensive datasets, and utilized a pre-trained language model. We conditioned the model with dataset-specific texts, enabling it to learn sound quality and recording environment based on text input. Moreover, we leveraged external language models to improve text descriptions of our datasets and performed "},"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":"2306.09807","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-16T12:44:10Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"0e4f0cff70c2dc2fda022142af3b068434a0d882b6833f25f5e78348abf6c928","abstract_canon_sha256":"42c00a1e864b2e228e28f4eb5abbe05fac3b5a0cc07a548a6c31beadb16f30f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:54.216535Z","signature_b64":"tFJtmjxruHID3R+l0zXPNzPb91Rk706PasDxsl1wRlj1/Ij+LUT2kF8RHeq4aYH8IR+yEqWQLKzzPnk5bA8wDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfbd36533f26dac6cf4a9ec906a2811849d42afce92269e129c5721efa1bcadf","last_reissued_at":"2026-07-05T06:39:54.216092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:54.216092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FALL-E: A Foley Sound Synthesis Model and Strategies","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ben Sangbae Chon, Hyeongi Moon, Kyungyun Lee, Minsung Kang, Sangshin Oh","submitted_at":"2023-06-16T12:44:10Z","abstract_excerpt":"This paper introduces FALL-E, a foley synthesis system and its training/inference strategies. The FALL-E model employs a cascaded approach comprising low-resolution spectrogram generation, spectrogram super-resolution, and a vocoder. We trained every sound-related model from scratch using our extensive datasets, and utilized a pre-trained language model. We conditioned the model with dataset-specific texts, enabling it to learn sound quality and recording environment based on text input. Moreover, we leveraged external language models to improve text descriptions of our datasets and performed "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09807","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/2306.09807/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":"2306.09807","created_at":"2026-07-05T06:39:54.216155+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.09807v2","created_at":"2026-07-05T06:39:54.216155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09807","created_at":"2026-07-05T06:39:54.216155+00:00"},{"alias_kind":"pith_short_12","alias_value":"366TMUZ7E3NM","created_at":"2026-07-05T06:39:54.216155+00:00"},{"alias_kind":"pith_short_16","alias_value":"366TMUZ7E3NMNT2K","created_at":"2026-07-05T06:39:54.216155+00:00"},{"alias_kind":"pith_short_8","alias_value":"366TMUZ7","created_at":"2026-07-05T06:39:54.216155+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/366TMUZ7E3NMNT2KT3EQNIUBDB","json":"https://pith.science/pith/366TMUZ7E3NMNT2KT3EQNIUBDB.json","graph_json":"https://pith.science/api/pith-number/366TMUZ7E3NMNT2KT3EQNIUBDB/graph.json","events_json":"https://pith.science/api/pith-number/366TMUZ7E3NMNT2KT3EQNIUBDB/events.json","paper":"https://pith.science/paper/366TMUZ7"},"agent_actions":{"view_html":"https://pith.science/pith/366TMUZ7E3NMNT2KT3EQNIUBDB","download_json":"https://pith.science/pith/366TMUZ7E3NMNT2KT3EQNIUBDB.json","view_paper":"https://pith.science/paper/366TMUZ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.09807&json=true","fetch_graph":"https://pith.science/api/pith-number/366TMUZ7E3NMNT2KT3EQNIUBDB/graph.json","fetch_events":"https://pith.science/api/pith-number/366TMUZ7E3NMNT2KT3EQNIUBDB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/366TMUZ7E3NMNT2KT3EQNIUBDB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/366TMUZ7E3NMNT2KT3EQNIUBDB/action/storage_attestation","attest_author":"https://pith.science/pith/366TMUZ7E3NMNT2KT3EQNIUBDB/action/author_attestation","sign_citation":"https://pith.science/pith/366TMUZ7E3NMNT2KT3EQNIUBDB/action/citation_signature","submit_replication":"https://pith.science/pith/366TMUZ7E3NMNT2KT3EQNIUBDB/action/replication_record"}},"created_at":"2026-07-05T06:39:54.216155+00:00","updated_at":"2026-07-05T06:39:54.216155+00:00"}