{"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/quality-aware-masked-diffusion-transformer","title":"Quality-aware Masked Diffusion Transformer for Enhanced Music Generation","arxiv_id":"2405.15863","date":"2024-05-24","proceeding":null,"authors":["Chang Li","Ruoyu Wang","Lijuan Liu","Jun Du","Yixuan Sun","Zilu Guo","Zhenrong Zhang","Yuan Jiang","Jianqing Gao","Feng Ma"],"abstract":"Text-to-music (TTM) generation, which converts textual descriptions into audio, opens up innovative avenues for multimedia creation. Achieving high quality and diversity in this process demands extensive, high-quality data, which are often scarce in available datasets. Most open-source datasets frequently suffer from issues like low-quality waveforms and low text-audio consistency, hindering the advancement of music generation models. To address these challenges, we propose a novel quality-aware training paradigm for generating high-quality, high-musicality music from large-scale, quality-imbalanced datasets. Additionally, by leveraging unique properties in the latent space of musical signals, we adapt and implement a masked diffusion transformer (MDT) model for the TTM task, showcasing its capacity for quality control and enhanced musicality. Furthermore, we introduce a three-stage caption refinement approach to address low-quality captions' issue. Experiments show state-of-the-art (SOTA) performance on benchmark datasets including MusicCaps and the Song-Describer Dataset with both objective and subjective metrics. Demo audio samples are available at https://qa-mdt.github.io/, code and pretrained checkpoints are open-sourced at https://github.com/ivcylc/OpenMusic.","url_abs":"https://arxiv.org/abs/2405.15863v4","url_pdf":"https://arxiv.org/pdf/2405.15863v4.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":"quality-aware-masked-diffusion-transformer","repo_url":"https://github.com/ivcylc/openmusic","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"quality-aware-masked-diffusion-transformer","repo_url":"https://github.com/ivcylc/qa-mdt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"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"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/music-generation-on-song-describer-dataset","task":"Music Generation","dataset":"Song Describer Dataset","model":"OpenMusic","rank_in_archive_order":1,"of":1,"metrics":{"FAD VGG":"1.01"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-music-generation-on-musiccaps","task":"Text-to-Music Generation","dataset":"MusicCaps","model":"OpenMusic (QA-MDT)","rank_in_archive_order":3,"of":21,"metrics":{"FAD":"1.65","IS":"2.80","KL_passt":"1.31"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.15863","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15863"}},"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/ivcylc/qa-mdt","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ivcylc/openmusic","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"unverified":3},"by_repo_kind":{"official":{"samples":7,"ran":4,"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":0,"samples":[{"code_sha256_prefix":"22310b73059fa8cb","entry":"calculate_relative_bandwidth","repo":"ivcylc/openmusic","repo_kind":"official","path":"audioldm_train/dataset_plugin.py","file_url":"https://github.com/ivcylc/openmusic/blob/HEAD/audioldm_train/dataset_plugin.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":"22310b73059fa8cb"}},{"code_sha256_prefix":"652fe4f51a3afce0","entry":"collate_fn","repo":"ivcylc/openmusic","repo_kind":"official","path":"audioldm_train/modules/audiomae/audiovisual_dataset.py","file_url":"https://github.com/ivcylc/openmusic/blob/HEAD/audioldm_train/modules/audiomae/audiovisual_dataset.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":"652fe4f51a3afce0"}},{"code_sha256_prefix":"b1368330cf0f5642","entry":"isimage","repo":"ivcylc/openmusic","repo_kind":"official","path":"audioldm_train/utilities/model_util.py","file_url":"https://github.com/ivcylc/openmusic/blob/HEAD/audioldm_train/utilities/model_util.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":"b1368330cf0f5642"}},{"code_sha256_prefix":"d72762b700feee6f","entry":"ismap","repo":"ivcylc/openmusic","repo_kind":"official","path":"audioldm_train/utilities/model_util.py","file_url":"https://github.com/ivcylc/openmusic/blob/HEAD/audioldm_train/utilities/model_util.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":"d72762b700feee6f"}},{"code_sha256_prefix":"0186ae56bb268a36","entry":"get_vits_phoneme_ids","repo":"ivcylc/openmusic","repo_kind":"official","path":"audioldm_train/dataset_plugin.py","file_url":"https://github.com/ivcylc/openmusic/blob/HEAD/audioldm_train/dataset_plugin.py","link_basis":"first_harvest_node","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":"0186ae56bb268a36"}},{"code_sha256_prefix":"ad984e4532566626","entry":"get_vits_phoneme_ids_no_padding","repo":"ivcylc/openmusic","repo_kind":"official","path":"audioldm_train/dataset_plugin.py","file_url":"https://github.com/ivcylc/openmusic/blob/HEAD/audioldm_train/dataset_plugin.py","link_basis":"first_harvest_node","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":"ad984e4532566626"}},{"code_sha256_prefix":"f9bd2e83191afad1","entry":"log_txt_as_img","repo":"ivcylc/openmusic","repo_kind":"official","path":"audioldm_train/utilities/model_util.py","file_url":"https://github.com/ivcylc/openmusic/blob/HEAD/audioldm_train/utilities/model_util.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":"f9bd2e83191afad1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}