{"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/adversarial-audio-synthesis","title":"Adversarial Audio Synthesis","arxiv_id":"1802.04208","date":"2018-02-12","proceeding":"ICLR 2019 5","authors":["Chris Donahue","Julian McAuley","Miller Puckette"],"abstract":"Audio signals are sampled at high temporal resolutions, and learning to\nsynthesize audio requires capturing structure across a range of timescales.\nGenerative adversarial networks (GANs) have seen wide success at generating\nimages that are both locally and globally coherent, but they have seen little\napplication to audio generation. In this paper we introduce WaveGAN, a first\nattempt at applying GANs to unsupervised synthesis of raw-waveform audio.\nWaveGAN is capable of synthesizing one second slices of audio waveforms with\nglobal coherence, suitable for sound effect generation. Our experiments\ndemonstrate that, without labels, WaveGAN learns to produce intelligible words\nwhen trained on a small-vocabulary speech dataset, and can also synthesize\naudio from other domains such as drums, bird vocalizations, and piano. We\ncompare WaveGAN to a method which applies GANs designed for image generation on\nimage-like audio feature representations, finding both approaches to be\npromising.","url_abs":"http://arxiv.org/abs/1802.04208v3","url_pdf":"http://arxiv.org/pdf/1802.04208v3.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":"adversarial-audio-synthesis","repo_url":"https://github.com/chrisdonahue/wavegan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-audio-synthesis","repo_url":"https://github.com/IBM/MAX-Audio-Sample-Generator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-audio-synthesis","repo_url":"https://github.com/LEChaney/AudioStyleGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-audio-synthesis","repo_url":"https://github.com/MaxHolmberg96/WaveGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-audio-synthesis","repo_url":"https://github.com/MurreyCode/wavegan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-audio-synthesis","repo_url":"https://github.com/ShaunBarry/wavegan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-audio-synthesis","repo_url":"https://github.com/SilverEngineered/WaveGan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-audio-synthesis","repo_url":"https://github.com/Yotsuyubi/wave-nr-gan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"adversarial-audio-synthesis","repo_url":"https://github.com/acheketa/cwavegan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"adversarial-audio-synthesis","repo_url":"https://github.com/adrienchaton/BERGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"adversarial-audio-synthesis","repo_url":"https://github.com/alexandervnikitin/tsgm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-audio-synthesis","repo_url":"https://github.com/cristiprg/wavegan-fork","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-audio-synthesis","repo_url":"https://github.com/csiki/v2a","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"adversarial-audio-synthesis","repo_url":"https://github.com/delijingyic/wavegan_phonology","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"adversarial-audio-synthesis","repo_url":"https://github.com/erik-buchholz/SoK-TrajGen","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-audio-synthesis","repo_url":"https://github.com/fromme0528/pytorch-WaveGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-audio-synthesis","repo_url":"https://github.com/hawkiyc/WaveGAN_for_12_Leads_ECG_Signals","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-audio-synthesis","repo_url":"https://github.com/mahotani/ADVERSARIAL-AUDIO-SYNTHESIS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-audio-synthesis","repo_url":"https://github.com/mostafaelaraby/wavegan-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-audio-synthesis","repo_url":"https://github.com/nicobernasconi/specgan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-audio-synthesis","repo_url":"https://github.com/paechi/wavegan-asr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-audio-synthesis","repo_url":"https://github.com/zassou65535/WaveGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"audio-generation","task_name":"Audio Generation"},{"task_slug":"audio-synthesis","task_name":"Audio Synthesis"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dcgan","method_name":"DCGAN"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"griffin-lim-algorithm","method_name":"Griffin-Lim Algorithm"},{"method_slug":"phase-shuffle","method_name":"Phase Shuffle"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"specgan","method_name":"SpecGAN"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"wgan-gp-loss","method_name":"WGAN-GP Loss"},{"method_slug":"wavegan","method_name":"WaveGAN"}],"datasets_introduced":[],"methods_introduced":[{"slug":"phase-shuffle","name":"Phase Shuffle","full_name":"Phase Shuffle"},{"slug":"specgan","name":"SpecGAN","full_name":"SpecGAN"},{"slug":"wavegan","name":"WaveGAN","full_name":"WaveGAN"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.04208","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.04208"}},"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/MaxHolmberg96/WaveGAN","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SilverEngineered/WaveGan","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MurreyCode/wavegan","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IBM/MAX-Audio-Sample-Generator","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cristiprg/wavegan-fork","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ShaunBarry/wavegan","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mahotani/ADVERSARIAL-AUDIO-SYNTHESIS","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/paechi/wavegan-asr","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mostafaelaraby/wavegan-pytorch","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/erik-buchholz/SoK-TrajGen","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alexandervnikitin/tsgm","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Yotsuyubi/wave-nr-gan","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hawkiyc/WaveGAN_for_12_Leads_ECG_Signals","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/adrienchaton/BERGAN","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zassou65535/WaveGAN","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nicobernasconi/specgan","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LEChaney/AudioStyleGAN","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chrisdonahue/wavegan","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fromme0528/pytorch-WaveGAN","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/acheketa/cwavegan","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/csiki/v2a","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/delijingyic/wavegan_phonology","reach":null}],"summary":{"ran_draft_wrong":2,"unverified":2},"by_repo_kind":{"listed":{"samples":2,"ran":0,"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":"330f6334fb6a3c24","entry":"find_model","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"330f6334fb6a3c24"}},{"code_sha256_prefix":"5e0281ad454dfda9","entry":"load_config","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"5e0281ad454dfda9"}},{"code_sha256_prefix":"c5d744a300317590","entry":"load_wavegan_discriminator","repo":"delijingyic/wavegan_phonology","repo_kind":"listed","path":"wavegan.py","file_url":"https://github.com/delijingyic/wavegan_phonology/blob/HEAD/wavegan.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":"c5d744a300317590"}},{"code_sha256_prefix":"5ceec827155542d8","entry":"load_wavegan_generator","repo":"delijingyic/wavegan_phonology","repo_kind":"listed","path":"wavegan.py","file_url":"https://github.com/delijingyic/wavegan_phonology/blob/HEAD/wavegan.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":"5ceec827155542d8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}