{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XMDYSOB42B5QHUDYMRBD5VETBY","short_pith_number":"pith:XMDYSOB4","schema_version":"1.0","canonical_sha256":"bb0789383cd07b03d07864423ed4930e0b515f6935bcb1f68132ee499b9aa44e","source":{"kind":"arxiv","id":"1812.08466","version":4},"attestation_state":"computed","paper":{"title":"Fr\\'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Dominik Roblek, Kevin Kilgour, Matthew Sharifi, Mauricio Zuluaga","submitted_at":"2018-12-20T10:28:00Z","abstract_excerpt":"We propose the Fr\\'echet Audio Distance (FAD), a novel, reference-free evaluation metric for music enhancement algorithms. We demonstrate how typical evaluation metrics for speech enhancement and blind source separation can fail to accurately measure the perceived effect of a wide variety of distortions. As an alternative, we propose adapting the Fr\\'echet Inception Distance (FID) metric used to evaluate generative image models to the audio domain. FAD is validated using a wide variety of artificial distortions and is compared to the signal based metrics signal to distortion ratio (SDR), cosin"},"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":"1812.08466","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-12-20T10:28:00Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"051cc8f9a358afca8681593572da7835e685da13dd7318ccd9e74b68e07a0232","abstract_canon_sha256":"1ff845c5e1faedddce458fb26346f973ac9be922e47ea32a205551b89c894c4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:09.273899Z","signature_b64":"1gYVi6ffwN7aEDa/z5/Ff5qKt5pFmbNdrbwPyih+CMKlMCVb8YQ2P5xaLrZZHdYAZ7DFxR577nRV9ABj1VwOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb0789383cd07b03d07864423ed4930e0b515f6935bcb1f68132ee499b9aa44e","last_reissued_at":"2026-05-17T23:56:09.273206Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:09.273206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fr\\'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Dominik Roblek, Kevin Kilgour, Matthew Sharifi, Mauricio Zuluaga","submitted_at":"2018-12-20T10:28:00Z","abstract_excerpt":"We propose the Fr\\'echet Audio Distance (FAD), a novel, reference-free evaluation metric for music enhancement algorithms. We demonstrate how typical evaluation metrics for speech enhancement and blind source separation can fail to accurately measure the perceived effect of a wide variety of distortions. As an alternative, we propose adapting the Fr\\'echet Inception Distance (FID) metric used to evaluate generative image models to the audio domain. FAD is validated using a wide variety of artificial distortions and is compared to the signal based metrics signal to distortion ratio (SDR), cosin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.08466","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1812.08466","created_at":"2026-05-17T23:56:09.273321+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.08466v4","created_at":"2026-05-17T23:56:09.273321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.08466","created_at":"2026-05-17T23:56:09.273321+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMDYSOB42B5Q","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMDYSOB42B5QHUDY","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMDYSOB4","created_at":"2026-05-18T12:33:01.666342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2605.21538","citing_title":"Academic Text-to-Music Grand Challenge: Datasets, Baselines, and Evaluation Methods","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18467","citing_title":"InstructAV2AV: Instruction-Guided Audio-Video Joint Editing","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2510.09065","citing_title":"MMAudioSep: Taming Video-to-Audio Generative Model Towards Video/Text-Queried Sound Separation","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2502.05139","citing_title":"Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound","ref_index":69,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09259","citing_title":"Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04547","citing_title":"Stage-adaptive audio diffusion modeling","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00329","citing_title":"Fast Text-to-Audio Generation with One-Step Sampling via Energy-Scoring and Auxiliary Contextual Representation Distillation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2410.13720","citing_title":"Movie Gen: A Cast of Media Foundation Models","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17986","citing_title":"Latent Fourier Transform","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05731","citing_title":"FoleyDesigner: Immersive Stereo Foley Generation with Precise Spatio-Temporal Alignment for Film Clips","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04348","citing_title":"OmniSonic: Towards Universal and Holistic Audio Generation from Video and Text","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XMDYSOB42B5QHUDYMRBD5VETBY","json":"https://pith.science/pith/XMDYSOB42B5QHUDYMRBD5VETBY.json","graph_json":"https://pith.science/api/pith-number/XMDYSOB42B5QHUDYMRBD5VETBY/graph.json","events_json":"https://pith.science/api/pith-number/XMDYSOB42B5QHUDYMRBD5VETBY/events.json","paper":"https://pith.science/paper/XMDYSOB4"},"agent_actions":{"view_html":"https://pith.science/pith/XMDYSOB42B5QHUDYMRBD5VETBY","download_json":"https://pith.science/pith/XMDYSOB42B5QHUDYMRBD5VETBY.json","view_paper":"https://pith.science/paper/XMDYSOB4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.08466&json=true","fetch_graph":"https://pith.science/api/pith-number/XMDYSOB42B5QHUDYMRBD5VETBY/graph.json","fetch_events":"https://pith.science/api/pith-number/XMDYSOB42B5QHUDYMRBD5VETBY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMDYSOB42B5QHUDYMRBD5VETBY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMDYSOB42B5QHUDYMRBD5VETBY/action/storage_attestation","attest_author":"https://pith.science/pith/XMDYSOB42B5QHUDYMRBD5VETBY/action/author_attestation","sign_citation":"https://pith.science/pith/XMDYSOB42B5QHUDYMRBD5VETBY/action/citation_signature","submit_replication":"https://pith.science/pith/XMDYSOB42B5QHUDYMRBD5VETBY/action/replication_record"}},"created_at":"2026-05-17T23:56:09.273321+00:00","updated_at":"2026-05-17T23:56:09.273321+00:00"}