{"url":"/method/wavevae","slug":"wavevae","name":"WaveVAE","full_name":"WaveVAE","full_name_withheld":false,"description_markdown":"**WaveVAE** is a generative audio model that can be used as a vocoder in text-to-speech systems. It is a [VAE](https://paperswithcode.com/method/vae) based model that can be trained from scratch by jointly optimizing the encoder $q\\_{\\phi}\\left(\\mathbf{z}|\\mathbf{x}, \\mathbf{c}\\right)$ and decoder $p\\_{\\theta}\\left(\\mathbf{x}|\\mathbf{z}, \\mathbf{c}\\right)$, where $\\mathbf{z}$ is latent variables and $\\mathbf{c}$ is the mel spectrogram conditioner. \r\n\r\nThe encoder of WaveVAE $q\\_{\\phi}\\left(\\mathbf{z}|\\mathbf{x}\\right)$ is parameterized by a Gaussian autoregressive [WaveNet](https://paperswithcode.com/method/wavenet) that maps the ground truth audio x into the same length latent representation $\\mathbf{z}$. The decoder $p\\_{\\theta}\\left(\\mathbf{x}|\\mathbf{z}\\right)$ is parameterized by the one-step ahead predictions from an inverse autoregressive flow.\r\n\r\nThe training objective is the ELBO for the observed $\\mathbf{x}$ in the VAE.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/1905.08459v3","title":"Non-Autoregressive Neural Text-to-Speech","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":"Generative Audio Models","url":"/methods/category/generative-audio-models","pwc_aliases":[]}],"n_papers_tagged":2,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"title":"Autoregressive Speech Synthesis with Next-Distribution Prediction","date":"2024-12-22","arxiv_id":"2412.16846","n_code_links":0,"syntology":null},{"paper":"/paper/parallel-neural-text-to-speech","title":"Non-Autoregressive Neural Text-to-Speech","date":"2019-05-21","arxiv_id":"1905.08459","n_code_links":2,"syntology":{"ran":2,"of":7,"unverified":5,"pointer_only":0}}],"papers_shown":2,"tasks":[{"task":"/task/text-to-speech","name":"Text to Speech","papers":2},{"task":"/task/text-to-speech-1","name":"text-to-speech","papers":2},{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/prediction","name":"Prediction","papers":1},{"task":"/task/speech-synthesis","name":"Speech Synthesis","papers":1},{"task":"/task/text-to-speech-synthesis","name":"Text-To-Speech Synthesis","papers":1}],"tasks_shown":7,"n_tasks":7,"usage_by_year":[{"year":"2019","papers":1},{"year":"2024","papers":1}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/wavevae"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}