{"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/picoaudio-enabling-precise-timestamp-and","title":"PicoAudio: Enabling Precise Timestamp and Frequency Controllability of Audio Events in Text-to-audio Generation","arxiv_id":"2407.02869","date":"2024-07-03","proceeding":null,"authors":["Zeyu Xie","Xuenan Xu","Zhizheng Wu","Mengyue Wu"],"abstract":"Recently, audio generation tasks have attracted considerable research interests. Precise temporal controllability is essential to integrate audio generation with real applications. In this work, we propose a temporal controlled audio generation framework, PicoAudio. PicoAudio integrates temporal information to guide audio generation through tailored model design. It leverages data crawling, segmentation, filtering, and simulation of fine-grained temporally-aligned audio-text data. Both subjective and objective evaluations demonstrate that PicoAudio dramantically surpasses current state-of-the-art generation models in terms of timestamp and occurrence frequency controllability. The generated samples are available on the demo website https://zeyuxie29.github.io/PicoAudio.github.io.","url_abs":"https://arxiv.org/abs/2407.02869v2","url_pdf":"https://arxiv.org/pdf/2407.02869v2.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"picoaudio-enabling-precise-timestamp-and","repo_url":"https://github.com/picoaudio/picoaudio","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.02869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02869"}},"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/picoaudio/picoaudio","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2,"ran_violates":2,"ran":4,"ran_honours":1,"ran_fixture":1,"unverified":2},"by_repo_kind":{"official":{"samples":12,"ran":10,"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":12,"samples":[{"code_sha256_prefix":"9fcdaa6e423e8aa7","entry":"Normalize","repo":"picoaudio/picoaudio","repo_kind":"official","path":"picoaudio/audioldm/variational_autoencoder/modules.py","file_url":"https://github.com/picoaudio/picoaudio/blob/HEAD/picoaudio/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":"picoaudio/picoaudio","repo_kind":"official","path":"picoaudio/audioldm/ldm.py","file_url":"https://github.com/picoaudio/picoaudio/blob/HEAD/picoaudio/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":"picoaudio/picoaudio","repo_kind":"official","path":"picoaudio/audioldm/utils.py","file_url":"https://github.com/picoaudio/picoaudio/blob/HEAD/picoaudio/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":"picoaudio/picoaudio","repo_kind":"official","path":"picoaudio/audioldm/utils.py","file_url":"https://github.com/picoaudio/picoaudio/blob/HEAD/picoaudio/audioldm/utils.py","link_basis":"first_harvest_node","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":"picoaudio/picoaudio","repo_kind":"official","path":"picoaudio/audioldm/utils.py","file_url":"https://github.com/picoaudio/picoaudio/blob/HEAD/picoaudio/audioldm/utils.py","link_basis":"first_harvest_node","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":"a26f85d7c72ef39a","entry":"get_padding","repo":"picoaudio/picoaudio","repo_kind":"official","path":"picoaudio/audioldm/hifigan/models.py","file_url":"https://github.com/picoaudio/picoaudio/blob/HEAD/picoaudio/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":"picoaudio/picoaudio","repo_kind":"official","path":"picoaudio/audioldm/variational_autoencoder/modules.py","file_url":"https://github.com/picoaudio/picoaudio/blob/HEAD/picoaudio/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":"409a71c470a245cd","entry":"make_batch_for_text_to_audio","repo":"picoaudio/picoaudio","repo_kind":"official","path":"picoaudio/audioldm/pipeline.py","file_url":"https://github.com/picoaudio/picoaudio/blob/HEAD/picoaudio/audioldm/pipeline.py","link_basis":"first_harvest_node","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":"picoaudio/picoaudio","repo_kind":"official","path":"picoaudio/audioldm/variational_autoencoder/modules.py","file_url":"https://github.com/picoaudio/picoaudio/blob/HEAD/picoaudio/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":"444fd0303f1aff5a","entry":"round_up_duration","repo":"picoaudio/picoaudio","repo_kind":"official","path":"picoaudio/audioldm/pipeline.py","file_url":"https://github.com/picoaudio/picoaudio/blob/HEAD/picoaudio/audioldm/pipeline.py","link_basis":"first_harvest_node","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":"840ad483fdc083ab","entry":"normalize_wav","repo":"picoaudio/picoaudio","repo_kind":"official","path":"picoaudio/utils/torch_tools.py","file_url":"https://github.com/picoaudio/picoaudio/blob/HEAD/picoaudio/utils/torch_tools.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":"840ad483fdc083ab"}},{"code_sha256_prefix":"46650166417c9ef5","entry":"pad_wav","repo":"picoaudio/picoaudio","repo_kind":"official","path":"picoaudio/utils/torch_tools.py","file_url":"https://github.com/picoaudio/picoaudio/blob/HEAD/picoaudio/utils/torch_tools.py","link_basis":"first_harvest_node","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":"46650166417c9ef5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}