{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/adapting-frechet-audio-distance-for","title":"Adapting Frechet Audio Distance for Generative Music Evaluation","arxiv_id":"2311.01616","date":"2023-11-02","proceeding":null,"authors":["Azalea Gui","Hannes Gamper","Sebastian Braun","Dimitra Emmanouilidou"],"abstract":"The growing popularity of generative music models underlines the need for perceptually relevant, objective music quality metrics. The Frechet Audio Distance (FAD) is commonly used for this purpose even though its correlation with perceptual quality is understudied. We show that FAD performance may be hampered by sample size bias, poor choice of audio embeddings, or the use of biased or low-quality reference sets. We propose reducing sample size bias by extrapolating scores towards an infinite sample size. Through comparisons with MusicCaps labels and a listening test we identify audio embeddings and music reference sets that yield FAD scores well-correlated with acoustic and musical quality. Our results suggest that per-song FAD can be useful to identify outlier samples and predict perceptual quality for a range of music sets and generative models. Finally, we release a toolkit that allows adapting FAD for generative music evaluation.","url_abs":"https://arxiv.org/abs/2311.01616v2","url_pdf":"https://arxiv.org/pdf/2311.01616v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"adapting-frechet-audio-distance-for","repo_url":"https://github.com/microsoft/fadtk","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"adapting-frechet-audio-distance-for","repo_url":"https://github.com/YoonjinXD/kadtk","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"adapting-frechet-audio-distance-for","repo_url":"https://github.com/dcase2024-task7-sound-scene-synthesis/fadtk","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"adapting-frechet-audio-distance-for","repo_url":"https://github.com/pablebe/gensvs_eval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"adapting-frechet-audio-distance-for","repo_url":"https://github.com/soham97/pam","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"fad","task_name":"FAD"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.01616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.01616"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/microsoft/fadtk","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dcase2024-task7-sound-scene-synthesis/fadtk","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/soham97/pam","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pablebe/gensvs_eval","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YoonjinXD/kadtk","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"ran_draft_wrong":1,"unverified":5},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1},"listed":{"samples":7,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"f13f3eddd329ff24","entry":"calc_embd_statistics","repo":"microsoft/fadtk","repo_kind":"official","path":"fadtk/fad.py","file_url":"https://github.com/microsoft/fadtk/blob/HEAD/fadtk/fad.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f13f3eddd329ff24"}},{"code_sha256_prefix":"ca4b05e19c89061a","entry":"create_prompt","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"ca4b05e19c89061a"}},{"code_sha256_prefix":"a8d84ccaebb23a2a","entry":"evaluate_pam","repo":"pablebe/gensvs_eval","repo_kind":"listed","path":"01_evaluation_and_correlation/pam_eval/pcc.py","file_url":"https://github.com/pablebe/gensvs_eval/blob/HEAD/01_evaluation_and_correlation/pam_eval/pcc.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a8d84ccaebb23a2a"}},{"code_sha256_prefix":"c8e9bc934b6ab42c","entry":"get_cache_embedding_path","repo":"microsoft/fadtk","repo_kind":"official","path":"fadtk/utils.py","file_url":"https://github.com/microsoft/fadtk/blob/HEAD/fadtk/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c8e9bc934b6ab42c"}},{"code_sha256_prefix":"9e1c1269ab3f61a7","entry":"load_task_dataframe","repo":"pablebe/gensvs_eval","repo_kind":"listed","path":"01_evaluation_and_correlation/pam_eval/pcc.py","file_url":"https://github.com/pablebe/gensvs_eval/blob/HEAD/01_evaluation_and_correlation/pam_eval/pcc.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9e1c1269ab3f61a7"}},{"code_sha256_prefix":"f42e113f46cfeb9c","entry":"add_gen_disc_column","repo":"pablebe/gensvs_eval","repo_kind":"listed","path":"01_evaluation_and_correlation/gensvs_eval_plots_and_csv_export.py","file_url":"https://github.com/pablebe/gensvs_eval/blob/HEAD/01_evaluation_and_correlation/gensvs_eval_plots_and_csv_export.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f42e113f46cfeb9c"}},{"code_sha256_prefix":"478f975b166d8aac","entry":"get_argparse_groups","repo":"pablebe/gensvs_eval","repo_kind":"listed","path":"00_training_and_inference/train_finetune_bigvgan.py","file_url":"https://github.com/pablebe/gensvs_eval/blob/HEAD/00_training_and_inference/train_finetune_bigvgan.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"478f975b166d8aac"}},{"code_sha256_prefix":"705be5651717fc89","entry":"get_audio_encoder","repo":"pablebe/gensvs_eval","repo_kind":"listed","path":"01_evaluation_and_correlation/pam_eval/PAM/models/audio.py","file_url":"https://github.com/pablebe/gensvs_eval/blob/HEAD/01_evaluation_and_correlation/pam_eval/PAM/models/audio.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"705be5651717fc89"}},{"code_sha256_prefix":"a0be35dc5fd90ded","entry":"pvalue_to_stars","repo":"pablebe/gensvs_eval","repo_kind":"listed","path":"01_evaluation_and_correlation/gensvs_eval_plots_and_csv_export.py","file_url":"https://github.com/pablebe/gensvs_eval/blob/HEAD/01_evaluation_and_correlation/gensvs_eval_plots_and_csv_export.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a0be35dc5fd90ded"}},{"code_sha256_prefix":"a197466fbd6f0714","entry":"sort_df_by_order_df","repo":"pablebe/gensvs_eval","repo_kind":"listed","path":"01_evaluation_and_correlation/gensvs_eval_fad_mse.py","file_url":"https://github.com/pablebe/gensvs_eval/blob/HEAD/01_evaluation_and_correlation/gensvs_eval_fad_mse.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a197466fbd6f0714"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}