{"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/taming-data-and-transformers-for-audio-1","title":"Taming Data and Transformers for Audio Generation","arxiv_id":"2406.19388","date":"2024-06-27","proceeding":"arXiv 2024 6","authors":["Moayed Haji-Ali","Willi Menapace","Aliaksandr Siarohin","Guha Balakrishnan","Vicente Ordonez"],"abstract":"The scalability of ambient sound generators is hindered by data scarcity, insufficient caption quality, and limited scalability in model architecture. This work addresses these challenges by advancing both data and model scaling. First, we propose an efficient and scalable dataset collection pipeline tailored for ambient audio generation, resulting in AutoReCap-XL, the largest ambient audio-text dataset with over 47 million clips. To provide high-quality textual annotations, we propose AutoCap, a high-quality automatic audio captioning model. By adopting a Q-Former module and leveraging audio metadata, AutoCap substantially enhances caption quality, reaching a CIDEr score of $83.2$, a $3.2\\%$ improvement over previous captioning models. Finally, we propose GenAu, a scalable transformer-based audio generation architecture that we scale up to 1.25B parameters. We demonstrate its benefits from data scaling with synthetic captions as well as model size scaling. When compared to baseline audio generators trained at similar size and data scale, GenAu obtains significant improvements of $4.7\\%$ in FAD score, $11.1\\%$ in IS, and $13.5\\%$ in CLAP score. Our code, model checkpoints, and dataset are publicly available.","url_abs":"https://arxiv.org/abs/2406.19388v4","url_pdf":"https://arxiv.org/pdf/2406.19388v4.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":"taming-data-and-transformers-for-audio-1","repo_url":"https://github.com/snap-research/GenAU","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"audio-generation","task_name":"Audio Generation"},{"task_slug":"audio-synthesis","task_name":"Audio Synthesis"},{"task_slug":"audio-captioning","task_name":"Audio captioning"},{"task_slug":"fad","task_name":"FAD"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-generation-on-audiocaps","task":"Audio Generation","dataset":"AudioCaps","model":"GenAu-Large","rank_in_archive_order":11,"of":23,"metrics":{"CLAP_MS":"0.668","FAD":"1.21","FD":"16.51"},"uses_additional_data":false},{"leaderboard":"/sota/audio-captioning-on-audiocaps","task":"Audio captioning","dataset":"AudioCaps","model":"AutoCap","rank_in_archive_order":5,"of":18,"metrics":{"CIDEr":"0.832","METEOR":"0.253","ROUGE":"0.518","ROUGE-L":"0.518","SPICE":"0.182","SPIDEr":"0.507"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.19388","atlas_url":"https://app.syntology.ai/?focus=2406.19388","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":"2406.19388"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2406.19388\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2406.19388"},"call":"get_concepts_for_paper(arxiv_id=\"2406.19388\")"}],"by_repo":[{"repo":"snap-research/GenAU","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":"53c45168b39c566b32fecf70628f00076cf993b7b81a11c3c1136afd99c2e3a2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}