{"url":"/method/wavegrad-dblock","slug":"wavegrad-dblock","name":"WaveGrad DBlock","full_name":"WaveGrad DBlock","full_name_withheld":false,"description_markdown":"**WaveGrad DBlocks** are used to downsample the temporal dimension of noisy waveform in [WaveGrad](https://paperswithcode.com/method/wavegrad). They are similar to UBlocks except that only one [residual block](https://paperswithcode.com/method/residual-block) is included. The dilation factors are 1, 2, 4 in the main branch. Orthogonal initialization is used.","description_state":"present","introduced_year":null,"introduced_by":{"title":"WaveGrad: Estimating Gradients for Waveform Generation","paper":"/paper/wavegrad-estimating-gradients-for-waveform","first_author":"Nanxin Chen","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/wavegrad-estimating-gradients-for-waveform"},"source":{"url":"https://arxiv.org/abs/2009.00713v2","title":"WaveGrad: Estimating Gradients for Waveform Generation","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Audio","area_id":"audio","collection":"Audio Model Blocks","url":"/methods/category/audio-model-blocks","pwc_aliases":[]}],"n_papers_tagged":7,"archive_num_papers":7,"papers_newest_first":[{"paper":null,"title":"GLA-Grad: A Griffin-Lim Extended Waveform Generation Diffusion Model","date":"2024-02-09","arxiv_id":"2402.15516","n_code_links":0,"syntology":null},{"paper":"/paper/bddm-bilateral-denoising-diffusion-models-for-1","title":"BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis","date":"2022-03-25","arxiv_id":"2203.13508","n_code_links":1,"syntology":{"ran":5,"of":6,"unverified":1,"pointer_only":0}},{"paper":null,"title":"InferGrad: Improving Diffusion Models for Vocoder by Considering Inference in Training","date":"2022-02-08","arxiv_id":"2202.03751","n_code_links":0,"syntology":null},{"paper":null,"title":"Quasi-Taylor Samplers for Diffusion Generative Models based on Ideal Derivatives","date":"2021-12-26","arxiv_id":"2112.13339","n_code_links":0,"syntology":null},{"paper":"/paper/vocbench-a-neural-vocoder-benchmark-for","title":"VocBench: A Neural Vocoder Benchmark for Speech Synthesis","date":"2021-12-06","arxiv_id":"2112.03099","n_code_links":1,"syntology":null},{"paper":"/paper/wavegrad-2-iterative-refinement-for-text-to","title":"WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis","date":"2021-06-17","arxiv_id":"2106.09660","n_code_links":3,"syntology":{"ran":2,"of":2,"unverified":0,"pointer_only":0}},{"paper":"/paper/wavegrad-estimating-gradients-for-waveform","title":"WaveGrad: Estimating Gradients for Waveform Generation","date":"2020-09-02","arxiv_id":"2009.00713","n_code_links":7,"syntology":{"ran":1,"of":3,"unverified":2,"pointer_only":1}}],"papers_shown":7,"tasks":[{"task":"/task/speech-synthesis","name":"Speech Synthesis","papers":5},{"task":"/task/denoising","name":"Denoising","papers":2},{"task":"/task/image-generation","name":"Image Generation","papers":2},{"task":"/task/text-to-speech-synthesis","name":"Text-To-Speech Synthesis","papers":2},{"task":"/task/text-to-speech","name":"Text to Speech","papers":1},{"task":"/task/text-to-speech-1","name":"text-to-speech","papers":1}],"tasks_shown":6,"n_tasks":6,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":3},{"year":"2022","papers":2},{"year":"2024","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/wavegrad-dblock"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}