{"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/prompt-guided-precise-audio-editing-with","title":"Prompt-guided Precise Audio Editing with Diffusion Models","arxiv_id":"2406.04350","date":"2024-05-11","proceeding":null,"authors":["Manjie Xu","Chenxing Li","Duzhen Zhang","Dan Su","Wei Liang","Dong Yu"],"abstract":"Audio editing involves the arbitrary manipulation of audio content through precise control. Although text-guided diffusion models have made significant advancements in text-to-audio generation, they still face challenges in finding a flexible and precise way to modify target events within an audio track. We present a novel approach, referred to as PPAE, which serves as a general module for diffusion models and enables precise audio editing. The editing is based on the input textual prompt only and is entirely training-free. We exploit the cross-attention maps of diffusion models to facilitate accurate local editing and employ a hierarchical local-global pipeline to ensure a smoother editing process. Experimental results highlight the effectiveness of our method in various editing tasks.","url_abs":"https://arxiv.org/abs/2406.04350v1","url_pdf":"https://arxiv.org/pdf/2406.04350v1.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":[],"tasks":[{"task_slug":"audio-generation","task_name":"Audio Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.04350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04350"}},"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":"deterministic:regex_extraction","url":"https://github.com/haoheliu/audioldm","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_draft_wrong":3,"ran_violates":2,"ran":8,"ran_honours":1,"ran_fixture":1,"unverified":3},"by_repo_kind":{"found_in_text":{"samples":18,"ran":15,"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":18,"samples":[{"code_sha256_prefix":"9fcdaa6e423e8aa7","entry":"Normalize","repo":"haoheliu/audioldm","repo_kind":"found_in_text","path":"audioldm/variational_autoencoder/modules.py","file_url":"https://github.com/haoheliu/audioldm/blob/HEAD/audioldm/variational_autoencoder/modules.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9fcdaa6e423e8aa7"}},{"code_sha256_prefix":"4cb732f513d69dfd","entry":"disabled_train","repo":"haoheliu/audioldm","repo_kind":"found_in_text","path":"audioldm/ldm.py","file_url":"https://github.com/haoheliu/audioldm/blob/HEAD/audioldm/ldm.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4cb732f513d69dfd"}},{"code_sha256_prefix":"608e364a9d2376a3","entry":"exists","repo":"haoheliu/audioldm","repo_kind":"found_in_text","path":"audioldm/utils.py","file_url":"https://github.com/haoheliu/audioldm/blob/HEAD/audioldm/utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"608e364a9d2376a3"}},{"code_sha256_prefix":"33e4f7a8bf80ee3a","entry":"get_bit_depth","repo":"haoheliu/audioldm","repo_kind":"found_in_text","path":"audioldm/utils.py","file_url":"https://github.com/haoheliu/audioldm/blob/HEAD/audioldm/utils.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":"33e4f7a8bf80ee3a"}},{"code_sha256_prefix":"159fc130dc64d332","entry":"get_duration","repo":"haoheliu/audioldm","repo_kind":"found_in_text","path":"audioldm/utils.py","file_url":"https://github.com/haoheliu/audioldm/blob/HEAD/audioldm/utils.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":"159fc130dc64d332"}},{"code_sha256_prefix":"8f1fbba0d901fc52","entry":"get_map","repo":"haoheliu/audioldm","repo_kind":"found_in_text","path":"audioldm/clap/open_clip/loss.py","file_url":"https://github.com/haoheliu/audioldm/blob/HEAD/audioldm/clap/open_clip/loss.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8f1fbba0d901fc52"}},{"code_sha256_prefix":"8934af0178d8697f","entry":"get_mel_from_wav","repo":"haoheliu/audioldm","repo_kind":"found_in_text","path":"audioldm/audio/tools.py","file_url":"https://github.com/haoheliu/audioldm/blob/HEAD/audioldm/audio/tools.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"8934af0178d8697f"}},{"code_sha256_prefix":"a26f85d7c72ef39a","entry":"get_padding","repo":"haoheliu/audioldm","repo_kind":"found_in_text","path":"audioldm/hifigan/models.py","file_url":"https://github.com/haoheliu/audioldm/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":"cb49209c125de1b4","entry":"get_timestep_embedding","repo":"haoheliu/audioldm","repo_kind":"found_in_text","path":"audioldm/variational_autoencoder/modules.py","file_url":"https://github.com/haoheliu/audioldm/blob/HEAD/audioldm/variational_autoencoder/modules.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cb49209c125de1b4"}},{"code_sha256_prefix":"9f9ec26d4cdfdf7d","entry":"griffin_lim","repo":"haoheliu/audioldm","repo_kind":"found_in_text","path":"audioldm/audio/audio_processing.py","file_url":"https://github.com/haoheliu/audioldm/blob/HEAD/audioldm/audio/audio_processing.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9f9ec26d4cdfdf7d"}},{"code_sha256_prefix":"409a71c470a245cd","entry":"make_batch_for_text_to_audio","repo":"haoheliu/audioldm","repo_kind":"found_in_text","path":"audioldm/pipeline.py","file_url":"https://github.com/haoheliu/audioldm/blob/HEAD/audioldm/pipeline.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":"409a71c470a245cd"}},{"code_sha256_prefix":"3137073275f8c21a","entry":"nonlinearity","repo":"haoheliu/audioldm","repo_kind":"found_in_text","path":"audioldm/variational_autoencoder/modules.py","file_url":"https://github.com/haoheliu/audioldm/blob/HEAD/audioldm/variational_autoencoder/modules.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3137073275f8c21a"}},{"code_sha256_prefix":"797c17f788edf908","entry":"normalize_wav","repo":"haoheliu/audioldm","repo_kind":"found_in_text","path":"audioldm/audio/tools.py","file_url":"https://github.com/haoheliu/audioldm/blob/HEAD/audioldm/audio/tools.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"797c17f788edf908"}},{"code_sha256_prefix":"1920008288771e41","entry":"pad_wav","repo":"haoheliu/audioldm","repo_kind":"found_in_text","path":"audioldm/audio/tools.py","file_url":"https://github.com/haoheliu/audioldm/blob/HEAD/audioldm/audio/tools.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1920008288771e41"}},{"code_sha256_prefix":"444fd0303f1aff5a","entry":"round_up_duration","repo":"haoheliu/audioldm","repo_kind":"found_in_text","path":"audioldm/pipeline.py","file_url":"https://github.com/haoheliu/audioldm/blob/HEAD/audioldm/pipeline.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"444fd0303f1aff5a"}},{"code_sha256_prefix":"0b80ec09e3ba47ae","entry":"dynamic_range_compression","repo":"haoheliu/audioldm","repo_kind":"found_in_text","path":"audioldm/audio/audio_processing.py","file_url":"https://github.com/haoheliu/audioldm/blob/HEAD/audioldm/audio/audio_processing.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":"0b80ec09e3ba47ae"}},{"code_sha256_prefix":"9b31c784540df0d7","entry":"gather_features","repo":"haoheliu/audioldm","repo_kind":"found_in_text","path":"audioldm/clap/open_clip/loss.py","file_url":"https://github.com/haoheliu/audioldm/blob/HEAD/audioldm/clap/open_clip/loss.py","link_basis":"plan_row","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":"9b31c784540df0d7"}},{"code_sha256_prefix":"473061649d09d30c","entry":"lp_gather_features","repo":"haoheliu/audioldm","repo_kind":"found_in_text","path":"audioldm/clap/open_clip/loss.py","file_url":"https://github.com/haoheliu/audioldm/blob/HEAD/audioldm/clap/open_clip/loss.py","link_basis":"plan_row","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":"473061649d09d30c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}