{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/etta-elucidating-the-design-space-of-text-to","title":"ETTA: Elucidating the Design Space of Text-to-Audio Models","arxiv_id":"2412.19351","date":"2024-12-26","proceeding":null,"authors":["Sang-gil Lee","Zhifeng Kong","Arushi Goel","Sungwon Kim","Rafael Valle","Bryan Catanzaro"],"abstract":"Recent years have seen significant progress in Text-To-Audio (TTA) synthesis, enabling users to enrich their creative workflows with synthetic audio generated from natural language prompts. Despite this progress, the effects of data, model architecture, training objective functions, and sampling strategies on target benchmarks are not well understood. With the purpose of providing a holistic understanding of the design space of TTA models, we set up a large-scale empirical experiment focused on diffusion and flow matching models. Our contributions include: 1) AF-Synthetic, a large dataset of high quality synthetic captions obtained from an audio understanding model; 2) a systematic comparison of different architectural, training, and inference design choices for TTA models; 3) an analysis of sampling methods and their Pareto curves with respect to generation quality and inference speed. We leverage the knowledge obtained from this extensive analysis to propose our best model dubbed Elucidated Text-To-Audio (ETTA). When evaluated on AudioCaps and MusicCaps, ETTA provides improvements over the baselines trained on publicly available data, while being competitive with models trained on proprietary data. Finally, we show ETTA's improved ability to generate creative audio following complex and imaginative captions -- a task that is more challenging than current benchmarks.","url_abs":"https://arxiv.org/abs/2412.19351v1","url_pdf":"https://arxiv.org/pdf/2412.19351v1.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":"etta-elucidating-the-design-space-of-text-to","repo_url":"https://github.com/NVIDIA/elucidated-text-to-audio","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"audio-generation","task_name":"Audio Generation"},{"task_slug":"audio-captioning","task_name":"Audio captioning"},{"task_slug":null,"task_name":"AudioCaps"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"music-generation","task_name":"Music Generation"},{"task_slug":"text-to-music-generation","task_name":"Text-to-Music Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-generation-on-audiocaps","task":"Audio Generation","dataset":"AudioCaps","model":"ETTA-FT-AC-100k","rank_in_archive_order":1,"of":23,"metrics":{"CLAP_LAION":"0.60","CLAP_MS":"0.43","FAD":"2.03","FD":"10.10","FD_openl3":"61.79","IS":"14.29","KL_passt":"1.13"},"uses_additional_data":false},{"leaderboard":"/sota/audio-generation-on-audiocaps","task":"Audio Generation","dataset":"AudioCaps","model":"ETTA","rank_in_archive_order":5,"of":23,"metrics":{"CLAP_LAION":"0.54","CLAP_MS":"0.43","FAD":"2.51","FD":"13.12","FD_openl3":"80.13","IS":"14.36","KL_passt":"1.22"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-music-generation-on-musiccaps","task":"Text-to-Music Generation","dataset":"MusicCaps","model":"ETTA","rank_in_archive_order":4,"of":21,"metrics":{"CLAP_LAION":"0.51","CLAP_MS":"0.53","FAD":"1.91","FD":"10.06","FD_openl3":"92.18","IS":"3.32","KL_passt":"0.84"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.19351","atlas_url":"https://app.syntology.ai/?focus=2412.19351","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2412.19351"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2412.19351\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2412.19351"},"call":"get_concepts_for_paper(arxiv_id=\"2412.19351\")"}],"by_repo":[{"repo":"NVIDIA/elucidated-text-to-audio","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"0fb43c66e23e5201b3ac45d7f5f8d73f5ba2a9d49b78346e1ceefda1d5610328","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}