{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4KQ52OF36REZAJP2EERE4JDR6A","short_pith_number":"pith:4KQ52OF3","schema_version":"1.0","canonical_sha256":"e2a1dd38bbf4499025fa21224e2471f016bba012e6831b9ea1b19e2d429d4396","source":{"kind":"arxiv","id":"2403.17508","version":1},"attestation_state":"computed","paper":{"title":"Correlation of Fr\\'echet Audio Distance With Human Perception of Environmental Audio Is Embedding Dependant","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Junwon Lee, Keisuke Imoto, Keunwoo Choi, Laurie M. Heller, Mathieu Lagrange, Modan Tailleur, Yuki Okamoto","submitted_at":"2024-03-26T09:09:59Z","abstract_excerpt":"This paper explores whether considering alternative domain-specific embeddings to calculate the Fr\\'echet Audio Distance (FAD) metric can help the FAD to correlate better with perceptual ratings of environmental sounds. We used embeddings from VGGish, PANNs, MS-CLAP, L-CLAP, and MERT, which are tailored for either music or environmental sound evaluation. The FAD scores were calculated for sounds from the DCASE 2023 Task 7 dataset. Using perceptual data from the same task, we find that PANNs-WGM-LogMel produces the best correlation between FAD scores and perceptual ratings of both audio quality"},"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":"2403.17508","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-03-26T09:09:59Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"4cd09129b746aa99b09092d0c00e9f6960291d68adfd8c1b634fb935d696043a","abstract_canon_sha256":"00158ec34f6ef3987aac1971623b58fff95be55e47917716dc1281175cf82344"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:51.557595Z","signature_b64":"yoZBzbZr7YaQmvC9l+0Evc0FeqsWlgDQfXBxuGFlBb/jL1j7GQ5bjiRFD6IH/iDE+lY3+pyO7sHQh9IBrKI6Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2a1dd38bbf4499025fa21224e2471f016bba012e6831b9ea1b19e2d429d4396","last_reissued_at":"2026-07-05T08:00:51.557140Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:51.557140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Correlation of Fr\\'echet Audio Distance With Human Perception of Environmental Audio Is Embedding Dependant","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Junwon Lee, Keisuke Imoto, Keunwoo Choi, Laurie M. Heller, Mathieu Lagrange, Modan Tailleur, Yuki Okamoto","submitted_at":"2024-03-26T09:09:59Z","abstract_excerpt":"This paper explores whether considering alternative domain-specific embeddings to calculate the Fr\\'echet Audio Distance (FAD) metric can help the FAD to correlate better with perceptual ratings of environmental sounds. We used embeddings from VGGish, PANNs, MS-CLAP, L-CLAP, and MERT, which are tailored for either music or environmental sound evaluation. The FAD scores were calculated for sounds from the DCASE 2023 Task 7 dataset. Using perceptual data from the same task, we find that PANNs-WGM-LogMel produces the best correlation between FAD scores and perceptual ratings of both audio quality"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17508","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/2403.17508/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":"2403.17508","created_at":"2026-07-05T08:00:51.557198+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.17508v1","created_at":"2026-07-05T08:00:51.557198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17508","created_at":"2026-07-05T08:00:51.557198+00:00"},{"alias_kind":"pith_short_12","alias_value":"4KQ52OF36REZ","created_at":"2026-07-05T08:00:51.557198+00:00"},{"alias_kind":"pith_short_16","alias_value":"4KQ52OF36REZAJP2","created_at":"2026-07-05T08:00:51.557198+00:00"},{"alias_kind":"pith_short_8","alias_value":"4KQ52OF3","created_at":"2026-07-05T08:00:51.557198+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00654","citing_title":"The Name-Free Gap: Policy-Aware Stylistic Control in Music Generation","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4KQ52OF36REZAJP2EERE4JDR6A","json":"https://pith.science/pith/4KQ52OF36REZAJP2EERE4JDR6A.json","graph_json":"https://pith.science/api/pith-number/4KQ52OF36REZAJP2EERE4JDR6A/graph.json","events_json":"https://pith.science/api/pith-number/4KQ52OF36REZAJP2EERE4JDR6A/events.json","paper":"https://pith.science/paper/4KQ52OF3"},"agent_actions":{"view_html":"https://pith.science/pith/4KQ52OF36REZAJP2EERE4JDR6A","download_json":"https://pith.science/pith/4KQ52OF36REZAJP2EERE4JDR6A.json","view_paper":"https://pith.science/paper/4KQ52OF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.17508&json=true","fetch_graph":"https://pith.science/api/pith-number/4KQ52OF36REZAJP2EERE4JDR6A/graph.json","fetch_events":"https://pith.science/api/pith-number/4KQ52OF36REZAJP2EERE4JDR6A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4KQ52OF36REZAJP2EERE4JDR6A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4KQ52OF36REZAJP2EERE4JDR6A/action/storage_attestation","attest_author":"https://pith.science/pith/4KQ52OF36REZAJP2EERE4JDR6A/action/author_attestation","sign_citation":"https://pith.science/pith/4KQ52OF36REZAJP2EERE4JDR6A/action/citation_signature","submit_replication":"https://pith.science/pith/4KQ52OF36REZAJP2EERE4JDR6A/action/replication_record"}},"created_at":"2026-07-05T08:00:51.557198+00:00","updated_at":"2026-07-05T08:00:51.557198+00:00"}