{"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/multi-band-melgan-faster-waveform-generation","title":"Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speech","arxiv_id":"2005.05106","date":"2020-05-11","proceeding":null,"authors":["Geng Yang","Shan Yang","Kai Liu","Peng Fang","Wei Chen","Lei Xie"],"abstract":"In this paper, we propose multi-band MelGAN, a much faster waveform generation model targeting to high-quality text-to-speech. Specifically, we improve the original MelGAN by the following aspects. First, we increase the receptive field of the generator, which is proven to be beneficial to speech generation. Second, we substitute the feature matching loss with the multi-resolution STFT loss to better measure the difference between fake and real speech. Together with pre-training, this improvement leads to both better quality and better training stability. More importantly, we extend MelGAN with multi-band processing: the generator takes mel-spectrograms as input and produces sub-band signals which are subsequently summed back to full-band signals as discriminator input. The proposed multi-band MelGAN has achieved high MOS of 4.34 and 4.22 in waveform generation and TTS, respectively. With only 1.91M parameters, our model effectively reduces the total computational complexity of the original MelGAN from 5.85 to 0.95 GFLOPS. Our Pytorch implementation, which will be open-resourced shortly, can achieve a real-time factor of 0.03 on CPU without hardware specific optimization.","url_abs":"https://arxiv.org/abs/2005.05106v1","url_pdf":"https://arxiv.org/pdf/2005.05106v1.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":"multi-band-melgan-faster-waveform-generation","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":"multi-band-melgan-faster-waveform-generation","repo_url":"https://github.com/TensorSpeech/TensorflowTTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"multi-band-melgan-faster-waveform-generation","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":"multi-band-melgan-faster-waveform-generation","repo_url":"https://github.com/cschaefer26/StyleMelGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"multi-band-melgan-faster-waveform-generation","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":"multi-band-melgan-faster-waveform-generation","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":"multi-band-melgan-faster-waveform-generation","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":"multi-band-melgan-faster-waveform-generation","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":"multi-band-melgan-faster-waveform-generation","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"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2005.05106","atlas_url":"https://app.syntology.ai/?focus=2005.05106","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05106"}},"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/cschaefer26/StyleMelGAN","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/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/yanggeng1995/FB-MelGAN","reach":null}],"summary":{"ran_draft_wrong":2,"unverified":5},"by_repo_kind":{"listed":{"samples":6,"ran":2,"repositories":4}},"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":2,"samples":[{"code_sha256_prefix":"83e2c862f7374ac7","entry":"dynamic_range_compression","repo":"rishikksh20/melgan","repo_kind":"listed","path":"utils/audio_processing.py","file_url":"https://github.com/rishikksh20/melgan/blob/HEAD/utils/audio_processing.py","link_basis":"harvester_set","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":"rishikksh20/melgan","repo_kind":"listed","path":"utils/audio_processing.py","file_url":"https://github.com/rishikksh20/melgan/blob/HEAD/utils/audio_processing.py","link_basis":"harvester_set","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":"9368459b15367fe4","entry":"attempt_to_restore","repo":"yanggeng1995/FB-MelGAN","repo_kind":"listed","path":"pre_train.py","file_url":"https://github.com/yanggeng1995/FB-MelGAN/blob/HEAD/pre_train.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":"9368459b15367fe4"}},{"code_sha256_prefix":"f443ef0155d2d898","entry":"load_checkpoint","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"f443ef0155d2d898"}},{"code_sha256_prefix":"d40b7ea72ed329ed","entry":"stft","repo":"rishikksh20/melgan","repo_kind":"listed","path":"utils/stft_loss.py","file_url":"https://github.com/rishikksh20/melgan/blob/HEAD/utils/stft_loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"d40b7ea72ed329ed"}},{"code_sha256_prefix":"d014b1a7520bc12b","entry":"stft","repo":"Moon-sung-woo/ParallelWaveGan_korean","repo_kind":"listed","path":"parallel_wavegan/losses/stft_loss.py","file_url":"https://github.com/Moon-sung-woo/ParallelWaveGan_korean/blob/HEAD/parallel_wavegan/losses/stft_loss.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":"d014b1a7520bc12b"}},{"code_sha256_prefix":"bebea9f2516460be","entry":"stft","repo":"rishikksh20/VocGAN","repo_kind":"listed","path":"utils/stft_loss.py","file_url":"https://github.com/rishikksh20/VocGAN/blob/HEAD/utils/stft_loss.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":"bebea9f2516460be"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}