{"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/make-an-audio-2-temporal-enhanced-text-to","title":"Make-An-Audio 2: Temporal-Enhanced Text-to-Audio Generation","arxiv_id":"2305.18474","date":"2023-05-29","proceeding":null,"authors":["Jiawei Huang","Yi Ren","Rongjie Huang","Dongchao Yang","Zhenhui Ye","Chen Zhang","Jinglin Liu","Xiang Yin","Zejun Ma","Zhou Zhao"],"abstract":"Large diffusion models have been successful in text-to-audio (T2A) synthesis tasks, but they often suffer from common issues such as semantic misalignment and poor temporal consistency due to limited natural language understanding and data scarcity. Additionally, 2D spatial structures widely used in T2A works lead to unsatisfactory audio quality when generating variable-length audio samples since they do not adequately prioritize temporal information. To address these challenges, we propose Make-an-Audio 2, a latent diffusion-based T2A method that builds on the success of Make-an-Audio. Our approach includes several techniques to improve semantic alignment and temporal consistency: Firstly, we use pre-trained large language models (LLMs) to parse the text into structured <event & order> pairs for better temporal information capture. We also introduce another structured-text encoder to aid in learning semantic alignment during the diffusion denoising process. To improve the performance of variable length generation and enhance the temporal information extraction, we design a feed-forward Transformer-based diffusion denoiser. Finally, we use LLMs to augment and transform a large amount of audio-label data into audio-text datasets to alleviate the problem of scarcity of temporal data. Extensive experiments show that our method outperforms baseline models in both objective and subjective metrics, and achieves significant gains in temporal information understanding, semantic consistency, and sound quality.","url_abs":"https://arxiv.org/abs/2305.18474v1","url_pdf":"https://arxiv.org/pdf/2305.18474v1.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":"make-an-audio-2-temporal-enhanced-text-to","repo_url":"https://github.com/bytedance/make-an-audio-2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"audio-generation","task_name":"Audio Generation"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"temporal-information-extraction","task_name":"Temporal Information Extraction"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-generation-on-audiocaps","task":"Audio Generation","dataset":"AudioCaps","model":"Make-An-Audio 2","rank_in_archive_order":17,"of":23,"metrics":{"FAD":"1.80","FD":"11.75"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.18474","atlas_url":"https://app.syntology.ai/?focus=2305.18474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18474"}},"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/bytedance/make-an-audio-2","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":5,"ran":4,"ran_violates":2,"unverified":1},"by_repo_kind":{"listed":{"samples":12,"ran":11,"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":"9fcdaa6e423e8aa7","entry":"Normalize","repo":"bytedance/make-an-audio-2","repo_kind":"listed","path":"ldm/models/autoencoder1d.py","file_url":"https://github.com/bytedance/make-an-audio-2/blob/HEAD/ldm/models/autoencoder1d.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9fcdaa6e423e8aa7"}},{"code_sha256_prefix":"70427d38625cc3ad","entry":"add_audio_path","repo":"bytedance/make-an-audio-2","repo_kind":"listed","path":"wav_evaluation/cal_clap_score.py","file_url":"https://github.com/bytedance/make-an-audio-2/blob/HEAD/wav_evaluation/cal_clap_score.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":"70427d38625cc3ad"}},{"code_sha256_prefix":"30048529b8b97c1c","entry":"cal_score_by_csv","repo":"bytedance/make-an-audio-2","repo_kind":"listed","path":"wav_evaluation/cal_clap_score.py","file_url":"https://github.com/bytedance/make-an-audio-2/blob/HEAD/wav_evaluation/cal_clap_score.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":"30048529b8b97c1c"}},{"code_sha256_prefix":"424012cb37b31172","entry":"default","repo":"bytedance/make-an-audio-2","repo_kind":"listed","path":"ldm/modules/attention.py","file_url":"https://github.com/bytedance/make-an-audio-2/blob/HEAD/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"424012cb37b31172"}},{"code_sha256_prefix":"0eb23950574e39a7","entry":"discriminator_loss_mse","repo":"bytedance/make-an-audio-2","repo_kind":"listed","path":"ldm/modules/losses_audio/contperceptual.py","file_url":"https://github.com/bytedance/make-an-audio-2/blob/HEAD/ldm/modules/losses_audio/contperceptual.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":"0eb23950574e39a7"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"bytedance/make-an-audio-2","repo_kind":"listed","path":"ldm/modules/attention.py","file_url":"https://github.com/bytedance/make-an-audio-2/blob/HEAD/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"22a83df891d750c6","entry":"hinge_d_loss","repo":"bytedance/make-an-audio-2","repo_kind":"listed","path":"ldm/modules/losses_audio/vqperceptual.py","file_url":"https://github.com/bytedance/make-an-audio-2/blob/HEAD/ldm/modules/losses_audio/vqperceptual.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"22a83df891d750c6"}},{"code_sha256_prefix":"af24442fe485c871","entry":"hinge_d_loss_with_exemplar_weights","repo":"bytedance/make-an-audio-2","repo_kind":"listed","path":"ldm/modules/losses_audio/vqperceptual.py","file_url":"https://github.com/bytedance/make-an-audio-2/blob/HEAD/ldm/modules/losses_audio/vqperceptual.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":"af24442fe485c871"}},{"code_sha256_prefix":"3137073275f8c21a","entry":"nonlinearity","repo":"bytedance/make-an-audio-2","repo_kind":"listed","path":"ldm/models/autoencoder1d.py","file_url":"https://github.com/bytedance/make-an-audio-2/blob/HEAD/ldm/models/autoencoder1d.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3137073275f8c21a"}},{"code_sha256_prefix":"9a299fe5ae09e407","entry":"uniq","repo":"bytedance/make-an-audio-2","repo_kind":"listed","path":"ldm/modules/attention.py","file_url":"https://github.com/bytedance/make-an-audio-2/blob/HEAD/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9a299fe5ae09e407"}},{"code_sha256_prefix":"263c54290c553ddd","entry":"vanilla_d_loss","repo":"bytedance/make-an-audio-2","repo_kind":"listed","path":"ldm/modules/losses_audio/vqperceptual.py","file_url":"https://github.com/bytedance/make-an-audio-2/blob/HEAD/ldm/modules/losses_audio/vqperceptual.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"263c54290c553ddd"}},{"code_sha256_prefix":"425b2c5baac91537","entry":"build_csv_from_wavs","repo":"bytedance/make-an-audio-2","repo_kind":"listed","path":"wav_evaluation/cal_clap_score.py","file_url":"https://github.com/bytedance/make-an-audio-2/blob/HEAD/wav_evaluation/cal_clap_score.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":"425b2c5baac91537"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}