{"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/melgan-generative-adversarial-networks-for","title":"MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis","arxiv_id":"1910.06711","date":"2019-10-08","proceeding":"NeurIPS 2019 12","authors":["Kundan Kumar","Rithesh Kumar","Thibault de Boissiere","Lucas Gestin","Wei Zhen Teoh","Jose Sotelo","Alexandre de Brebisson","Yoshua Bengio","Aaron Courville"],"abstract":"Previous works (Donahue et al., 2018a; Engel et al., 2019a) have found that generating coherent raw audio waveforms with GANs is challenging. In this paper, we show that it is possible to train GANs reliably to generate high quality coherent waveforms by introducing a set of architectural changes and simple training techniques. Subjective evaluation metric (Mean Opinion Score, or MOS) shows the effectiveness of the proposed approach for high quality mel-spectrogram inversion. To establish the generality of the proposed techniques, we show qualitative results of our model in speech synthesis, music domain translation and unconditional music synthesis. We evaluate the various components of the model through ablation studies and suggest a set of guidelines to design general purpose discriminators and generators for conditional sequence synthesis tasks. Our model is non-autoregressive, fully convolutional, with significantly fewer parameters than competing models and generalizes to unseen speakers for mel-spectrogram inversion. Our pytorch implementation runs at more than 100x faster than realtime on GTX 1080Ti GPU and more than 2x faster than real-time on CPU, without any hardware specific optimization tricks.","url_abs":"https://arxiv.org/abs/1910.06711v3","url_pdf":"https://arxiv.org/pdf/1910.06711v3.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":"melgan-generative-adversarial-networks-for","repo_url":"https://github.com/descriptinc/melgan-neurips","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"melgan-generative-adversarial-networks-for","repo_url":"https://github.com/MattSegal/speech-enhancement","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"melgan-generative-adversarial-networks-for","repo_url":"https://github.com/Mixergi/MelGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"melgan-generative-adversarial-networks-for","repo_url":"https://github.com/Moon-sung-woo/ParallelWaveGan_korean","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"melgan-generative-adversarial-networks-for","repo_url":"https://github.com/TensorSpeech/TensorflowTTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"melgan-generative-adversarial-networks-for","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":"melgan-generative-adversarial-networks-for","repo_url":"https://github.com/avi33/universalmelgan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"melgan-generative-adversarial-networks-for","repo_url":"https://github.com/coqui-ai/TTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MPL-2.0"}},{"paper_slug":"melgan-generative-adversarial-networks-for","repo_url":"https://github.com/dathudeptrai/TensorflowTTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"melgan-generative-adversarial-networks-for","repo_url":"https://github.com/deciding/ParallelWaveGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"melgan-generative-adversarial-networks-for","repo_url":"https://github.com/jacksonkaunismaa/neural-music","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"melgan-generative-adversarial-networks-for","repo_url":"https://github.com/jaywalnut310/melgan-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"melgan-generative-adversarial-networks-for","repo_url":"https://github.com/rishikksh20/VocGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"melgan-generative-adversarial-networks-for","repo_url":"https://github.com/rishikksh20/melgan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"melgan-generative-adversarial-networks-for","repo_url":"https://github.com/rosinality/melgan-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"melgan-generative-adversarial-networks-for","repo_url":"https://github.com/seungwonpark/melgan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"melgan-generative-adversarial-networks-for","repo_url":"https://github.com/yanggeng1995/FB-MelGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"melgan-generative-adversarial-networks-for","repo_url":"https://github.com/yanggeng1995/GAN-TTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"melgan-generative-adversarial-networks-for","repo_url":"https://github.com/2023-MindSpore-1/ms-code-74","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"melgan-generative-adversarial-networks-for","repo_url":"https://github.com/PaddlePaddle/PaddleSpeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"melgan-generative-adversarial-networks-for","repo_url":"https://github.com/mindspore-ai/models/tree/master/official/audio/melgan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dilated-convolution","method_name":"Dilated Convolution"},{"method_slug":"gan-hinge-loss","method_name":"GAN Hinge Loss"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"melgan","method_name":"MelGAN"},{"method_slug":"melgan-residual-block","method_name":"MelGAN Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"vq-vae","method_name":"VQ-VAE"},{"method_slug":"weight-normalization","method_name":"Weight Normalization"},{"method_slug":"window-based-discriminator","method_name":"Window-based Discriminator"}],"datasets_introduced":[],"methods_introduced":[{"slug":"melgan","name":"MelGAN","full_name":"MelGAN"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.06711","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.06711"}},"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/jaywalnut310/melgan-pytorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Mixergi/MelGAN","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PaddleSpeech","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TensorSpeech/TensorflowTTS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deciding/ParallelWaveGAN","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rishikksh20/VocGAN","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/descriptinc/melgan-neurips","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MattSegal/speech-enhancement","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dathudeptrai/TensorflowTTS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-1/ms-code-74","reach":{"status":"ok"}},{"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/yanggeng1995/GAN-TTS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/avi33/universalmelgan","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rosinality/melgan-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/coqui-ai/TTS","reach":{"status":"ok","spdx":"MPL-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Moon-sung-woo/ParallelWaveGan_korean","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rishikksh20/melgan","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/seungwonpark/melgan","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yanggeng1995/FB-MelGAN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jacksonkaunismaa/neural-music","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-ai/models/tree/master/official/audio/melgan","reach":null}],"summary":{"ran_violates":1,"ran_draft_wrong":4,"unverified":2},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":6,"ran":5,"repositories":3}},"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":1,"samples":[{"code_sha256_prefix":"f1f581545c4a0ab0","entry":"calc_padding","repo":"rosinality/melgan-pytorch","repo_kind":"listed","path":"melgan.py","file_url":"https://github.com/rosinality/melgan-pytorch/blob/HEAD/melgan.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f1f581545c4a0ab0"}},{"code_sha256_prefix":"83e2c862f7374ac7","entry":"dynamic_range_compression","repo":"seungwonpark/melgan","repo_kind":"listed","path":"utils/audio_processing.py","file_url":"https://github.com/seungwonpark/melgan/blob/HEAD/utils/audio_processing.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"83e2c862f7374ac7"}},{"code_sha256_prefix":"9f9ec26d4cdfdf7d","entry":"griffin_lim","repo":"seungwonpark/melgan","repo_kind":"listed","path":"utils/audio_processing.py","file_url":"https://github.com/seungwonpark/melgan/blob/HEAD/utils/audio_processing.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"9f9ec26d4cdfdf7d"}},{"code_sha256_prefix":"adbaa42086223bfc","entry":"wnconv1d","repo":"rosinality/melgan-pytorch","repo_kind":"listed","path":"melgan.py","file_url":"https://github.com/rosinality/melgan-pytorch/blob/HEAD/melgan.py","link_basis":"first_harvest_node","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":"adbaa42086223bfc"}},{"code_sha256_prefix":"d7b8ead7dfdd315e","entry":"wnconvtranspose1d","repo":"rosinality/melgan-pytorch","repo_kind":"listed","path":"melgan.py","file_url":"https://github.com/rosinality/melgan-pytorch/blob/HEAD/melgan.py","link_basis":"first_harvest_node","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":"d7b8ead7dfdd315e"}},{"code_sha256_prefix":"6e8184ff4faf3139","entry":"files_to_list","repo":"descriptinc/melgan-neurips","repo_kind":"official","path":"mel2wav/dataset.py","file_url":"https://github.com/descriptinc/melgan-neurips/blob/HEAD/mel2wav/dataset.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":"6e8184ff4faf3139"}},{"code_sha256_prefix":"f443ef0155d2d898","entry":"load_checkpoint","repo":"yanggeng1995/GAN-TTS","repo_kind":"listed","path":"generate.py","file_url":"https://github.com/yanggeng1995/GAN-TTS/blob/HEAD/generate.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":"f443ef0155d2d898"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}