{"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/2406-15487","title":"Improving Text-To-Audio Models with Synthetic Captions","arxiv_id":"2406.15487","date":"2024-06-18","proceeding":null,"authors":["Zhifeng Kong","Sang-gil Lee","Deepanway Ghosal","Navonil Majumder","Ambuj Mehrish","Rafael Valle","Soujanya Poria","Bryan Catanzaro"],"abstract":"It is an open challenge to obtain high quality training data, especially captions, for text-to-audio models. Although prior methods have leveraged \\textit{text-only language models} to augment and improve captions, such methods have limitations related to scale and coherence between audio and captions. In this work, we propose an audio captioning pipeline that uses an \\textit{audio language model} to synthesize accurate and diverse captions for audio at scale. We leverage this pipeline to produce a dataset of synthetic captions for AudioSet, named \\texttt{AF-AudioSet}, and then evaluate the benefit of pre-training text-to-audio models on these synthetic captions. Through systematic evaluations on AudioCaps and MusicCaps, we find leveraging our pipeline and synthetic captions leads to significant improvements on audio generation quality, achieving a new \\textit{state-of-the-art}.","url_abs":"https://arxiv.org/abs/2406.15487v2","url_pdf":"https://arxiv.org/pdf/2406.15487v2.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":"2406-15487","repo_url":"https://github.com/declare-lab/tango","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-captioning","task_name":"Audio captioning"},{"task_slug":null,"task_name":"AudioCaps"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"text-to-music-generation","task_name":"Text-to-Music Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-generation-on-audiocaps","task":"Audio Generation","dataset":"AudioCaps","model":"Tango-AF&AC-FT-AC","rank_in_archive_order":21,"of":23,"metrics":{"CLAP_LAION":"0.527","FAD":"2.54","FD":"17.19","IS":"11.04"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-music-generation-on-musiccaps","task":"Text-to-Music Generation","dataset":"MusicCaps","model":"TANGO-AF","rank_in_archive_order":7,"of":21,"metrics":{"CLAP_LAION":"0.51","CLAP_MS":"0.43","FAD":"2.21","FD":"22.69","FD_openl3":"270.32","IS":"2.79","KL_passt":"0.94"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.15487","atlas_url":"https://app.syntology.ai/?focus=2406.15487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.15487"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/declare-lab/tango","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":2,"ran_honours":1,"unverified":1},"by_repo_kind":{"listed":{"samples":4,"ran":3,"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":4,"samples":[{"code_sha256_prefix":"44ee71ec7cb0bca2","entry":"build_relative_position","repo":"declare-lab/tango","repo_kind":"listed","path":"mustango/modelling_deberta_v2.py","file_url":"https://github.com/declare-lab/tango/blob/HEAD/mustango/modelling_deberta_v2.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"44ee71ec7cb0bca2"}},{"code_sha256_prefix":"a26f85d7c72ef39a","entry":"get_padding","repo":"declare-lab/tango","repo_kind":"listed","path":"audioldm/hifigan/models.py","file_url":"https://github.com/declare-lab/tango/blob/HEAD/audioldm/hifigan/models.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"code_sha256_prefix":"cde5a0a5f4074d68","entry":"make_log_bucket_position","repo":"declare-lab/tango","repo_kind":"listed","path":"mustango/modelling_deberta_v2.py","file_url":"https://github.com/declare-lab/tango/blob/HEAD/mustango/modelling_deberta_v2.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cde5a0a5f4074d68"}},{"code_sha256_prefix":"11c7e96cb235d1f7","entry":"get_mask","repo":"declare-lab/tango","repo_kind":"listed","path":"mustango/modelling_deberta_v2.py","file_url":"https://github.com/declare-lab/tango/blob/HEAD/mustango/modelling_deberta_v2.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"11c7e96cb235d1f7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}