{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T19:17:17Z","timestamp":1791487037783,"version":"4.3.4"},"reference-count":26,"publisher":"IEEE","funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383551","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T16:46:54Z","timestamp":1616690814000},"page":"492-498","source":"Crossref","is-referenced-by-count":134,"title":["Multi-Band Melgan: Faster Waveform Generation For High-Quality Text-To-Speech"],"prefix":"10.1109","author":[{"given":"Geng","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","first-page":"10215","article-title":"Glow: Generative Flow with Invertible 1x1 Convolutions","author":"kingma","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"NICE: Non-linear Independent Components Estimation","author":"dinh","year":"2014"},{"key":"ref12","article-title":"Density estimation using Real NVP","author":"dinh","year":"2016"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref14","article-title":"FloWaveNet : A Generative Flow for Raw Audio","author":"kim","year":"2018"},{"key":"ref15","first-page":"2672","article-title":"Generative Adversarial Nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"5767","article-title":"Improved Training of Wasserstein GANs","author":"gulrajani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","author":"karras","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref19","article-title":"Video-to-Video Synthesis","author":"wang","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref3","article-title":"SampleRNN: An Unconditional End-to-End Neural Audio Generation Model","author":"mehri","year":"2016"},{"key":"ref6","article-title":"DurIAN: Duration Informed Attention Network For Multimodal Synthesis","author":"yu","year":"2019"},{"key":"ref5","article-title":"A Real-Time Wideband Neural Vocoder at 1.6 kb\/s Using LPCNet","author":"valin","year":"2019"},{"key":"ref8","article-title":"ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech","author":"ping","year":"2018"},{"key":"ref7","article-title":"Parallel WaveNet: Fast High-Fidelity Speech Synthesis","author":"van den oord","year":"2017"},{"key":"ref2","article-title":"Efficient Neural Audio Synthesis","author":"kalchbrenner","year":"2018"},{"key":"ref9","first-page":"4743","article-title":"Improved Variational Inference with Inverse Autoregressive Flow","author":"kingma","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref1","article-title":"WaveNet: A Generative Model for Raw Audio","author":"van den oord","year":"2016"},{"key":"ref20","first-page":"14881","article-title":"MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis","author":"kumar","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"High Fidelity Speech Synthesis with Adversarial Networks","author":"bi?kowski","year":"2019"},{"key":"ref21","article-title":"Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram","author":"yamamoto","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2880284"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1965"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref25","article-title":"Adam: A Method for Stochastic Optimization","author":"kingma","year":"2014"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","location":"Shenzhen, China","start":{"date-parts":[[2021,1,19]]},"end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383551.pdf?arnumber=9383551","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,8]],"date-time":"2021-06-08T14:52:16Z","timestamp":1623163936000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383551\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383551","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}