{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T15:39:00Z","timestamp":1771515540478,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746690","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"8432-8436","source":"Crossref","is-referenced-by-count":16,"title":["Infergrad: Improving Diffusion Models for Vocoder by Considering Inference in Training"],"prefix":"10.1109","author":[{"given":"Zehua","family":"Chen","sequence":"first","affiliation":[{"name":"Imperial College London,Department of EEE,London,UK,SW7 2AZ"}]},{"given":"Xu","family":"Tan","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia,Beijing,China,100080"}]},{"given":"Ke","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Azure Speech,Beijing,China,100080"}]},{"given":"Shifeng","family":"Pan","sequence":"additional","affiliation":[{"name":"Microsoft Azure Speech,Beijing,China,100080"}]},{"given":"Danilo","family":"Mandic","sequence":"additional","affiliation":[{"name":"Imperial College London,Department of EEE,London,UK,SW7 2AZ"}]},{"given":"Lei","family":"He","sequence":"additional","affiliation":[{"name":"Microsoft Azure Speech,Beijing,China,100080"}]},{"given":"Sheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Microsoft Azure Speech,Beijing,China,100080"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref10","article-title":"Non-autoregressive neural text-to-speech","author":"peng","year":"2020","journal-title":"ICML"},{"key":"ref11","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019","journal-title":"NeurIPS"},{"key":"ref12","article-title":"High fidelity speech synthesis with adversarial networks","author":"binkowski","year":"2020","journal-title":"ICLRE"},{"key":"ref13","article-title":"Generative modeling by estimating gradients of the data distribution","author":"song","year":"2019","journal-title":"NeurIPS"},{"key":"ref14","article-title":"Denoising diffusion probabilistic models","author":"ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref15","article-title":"Score-based generative modeling through stochastic differential equations","author":"song","year":"2021","journal-title":"ICLRE"},{"key":"ref16","article-title":"Variational diffusion models","author":"kingma","year":"2021","journal-title":"NeurIPS"},{"key":"ref17","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"kong","year":"2021","journal-title":"ICLRE"},{"key":"ref18","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","author":"popov","year":"2021","journal-title":"ICML"},{"key":"ref19","article-title":"Priorgrad: Improving conditional denoising diffusion models with data-driven adaptive prior","author":"lee","year":"2022","journal-title":"ICLRE"},{"key":"ref4","article-title":"A survey on neural speech synthesis","author":"tan","year":"2021"},{"key":"ref28","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"key":"ref27","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"MICCAI"},{"key":"ref3","article-title":"Wavegrad: Estimating gradients for waveform generation","author":"chen","year":"2021","journal-title":"ICLRE"},{"key":"ref6","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"ICML"},{"key":"ref5","article-title":"Samplernn: An unconditional end-to-end neural audio generation model","author":"mehri","year":"2017","journal-title":"ICLRE"},{"key":"ref29","article-title":"auraloss: Audio focused loss functions in PyTorch","author":"steinmetz","year":"2020","journal-title":"Digital Music Research Network One-day workshop"},{"key":"ref8","article-title":"Parallel wavenet: Fast high-fidelity speech synthesis","author":"oord","year":"2018","journal-title":"ICML"},{"key":"ref7","article-title":"Variational inference with normalizing flows","author":"rezende","year":"2015","journal-title":"ICML"},{"key":"ref2","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref1","article-title":"Wavenet: A generative model for raw audio","author":"oord","year":"2016"},{"key":"ref9","article-title":"Glow: Generative flow with invertible 1x1 convolutions","author":"kingma","year":"2018","journal-title":"NeurIPS"},{"key":"ref20","article-title":"Lsgm: Score-based generative modeling in latent space","author":"vahdat","year":"2021","journal-title":"NeurIPS"},{"key":"ref22","article-title":"Noise estimation for generative diffusion models","author":"san-romanm","year":"2021"},{"key":"ref21","article-title":"Bilateral denoising diffusion models","author":"lam","year":"2022","journal-title":"ICLRE"},{"key":"ref24","article-title":"Diffusion models beat gans on image synthesis","author":"dhariwal","year":"2021","journal-title":"NeurIPS"},{"key":"ref23","article-title":"Denoising diffusion implicit models","author":"song","year":"2021","journal-title":"ICLRE"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref25","article-title":"The LJ speech dataset","author":"ito","year":"2017"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746690.pdf?arnumber=9746690","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:14:21Z","timestamp":1661199261000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746690\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746690","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}