{"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/wavegrad-estimating-gradients-for-waveform","title":"WaveGrad: Estimating Gradients for Waveform Generation","arxiv_id":"2009.00713","date":"2020-09-02","proceeding":"ICLR 2021 1","authors":["Nanxin Chen","Yu Zhang","Heiga Zen","Ron J. Weiss","Mohammad Norouzi","William Chan"],"abstract":"This paper introduces WaveGrad, a conditional model for waveform generation which estimates gradients of the data density. The model is built on prior work on score matching and diffusion probabilistic models. It starts from a Gaussian white noise signal and iteratively refines the signal via a gradient-based sampler conditioned on the mel-spectrogram. WaveGrad offers a natural way to trade inference speed for sample quality by adjusting the number of refinement steps, and bridges the gap between non-autoregressive and autoregressive models in terms of audio quality. We find that it can generate high fidelity audio samples using as few as six iterations. Experiments reveal WaveGrad to generate high fidelity audio, outperforming adversarial non-autoregressive baselines and matching a strong likelihood-based autoregressive baseline using fewer sequential operations. Audio samples are available at https://wavegrad.github.io/.","url_abs":"https://arxiv.org/abs/2009.00713v2","url_pdf":"https://arxiv.org/pdf/2009.00713v2.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":"wavegrad-estimating-gradients-for-waveform","repo_url":"https://github.com/acids-ircam/diffusion_models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"wavegrad-estimating-gradients-for-waveform","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":"wavegrad-estimating-gradients-for-waveform","repo_url":"https://github.com/ivanvovk/WaveGrad","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"wavegrad-estimating-gradients-for-waveform","repo_url":"https://github.com/lmnt-com/wavegrad","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"wavegrad-estimating-gradients-for-waveform","repo_url":"https://github.com/maum-ai/wavegrad2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"wavegrad-estimating-gradients-for-waveform","repo_url":"https://github.com/mindslab-ai/wavegrad2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"wavegrad-estimating-gradients-for-waveform","repo_url":"https://github.com/keonlee9420/WaveGrad2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"text-to-speech-synthesis","task_name":"Text-To-Speech Synthesis"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"anti-alias-downsampling","method_name":"Anti-Alias Downsampling"},{"method_slug":"assemble-resnet","method_name":"Assemble-ResNet"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"big-little-module","method_name":"Big-Little Module"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"dilated-convolution","method_name":"Dilated Convolution"},{"method_slug":"film-module","method_name":"FiLM Module"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"resnet-d","method_name":"ResNet-D"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"selective-kernel","method_name":"Selective Kernel"},{"method_slug":"selective-kernel-convolution","method_name":"Selective Kernel Convolution"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"wavegrad","method_name":"WaveGrad"},{"method_slug":"wavegrad-dblock","method_name":"WaveGrad DBlock"},{"method_slug":"wavegrad-ublock","method_name":"WaveGrad UBlock"},{"method_slug":"xavier-initialization","method_name":"Xavier Initialization"}],"datasets_introduced":[],"methods_introduced":[{"slug":"wavegrad","name":"WaveGrad","full_name":"WaveGrad"},{"slug":"wavegrad-dblock","name":"WaveGrad DBlock","full_name":"WaveGrad DBlock"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2009.00713","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.00713"}},"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/lmnt-com/wavegrad","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/maum-ai/wavegrad2","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/acids-ircam/diffusion_models","reach":{"status":"ok"}},{"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/ivanvovk/WaveGrad","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindslab-ai/wavegrad2","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/keonlee9420/WaveGrad2","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"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":1,"samples":[{"code_sha256_prefix":"2b5c06c1ba593c3c","entry":"read_lexicon","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":"2b5c06c1ba593c3c"}},{"code_sha256_prefix":"7caaa0fdf8acf7bc","entry":"compute_rtf","repo":"ivanvovk/WaveGrad","repo_kind":"listed","path":"benchmark.py","file_url":"https://github.com/ivanvovk/WaveGrad/blob/HEAD/benchmark.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":"7caaa0fdf8acf7bc"}},{"code_sha256_prefix":"f2ebc6b7e9aea19b","entry":"generate_betas_grid","repo":"ivanvovk/WaveGrad","repo_kind":"listed","path":"benchmark.py","file_url":"https://github.com/ivanvovk/WaveGrad/blob/HEAD/benchmark.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":"f2ebc6b7e9aea19b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}