{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T20:47:23Z","timestamp":1791578843299,"version":"4.3.4"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413851","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"5679-5683","source":"Crossref","is-referenced-by-count":57,"title":["Wave-Tacotron: Spectrogram-Free End-to-End Text-to-Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Ron J.","family":"Weiss","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"RJ","family":"Skerry-Ryan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Battenberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soroosh","family":"Mariooryad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Diederik P.","family":"Kingma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","article-title":"FastSpeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref32","first-page":"359","article-title":"Using dynamic time warping to find patterns in time series","author":"berndt","year":"1994","journal-title":"Proceedings of the International Conference on Knowledge Discovery and Data Mining"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref35","article-title":"WaveGrad: Estimating gradients for waveform generation","author":"chen","year":"2021","journal-title":"Proc International Conference on Learning Representations"},{"key":"ref34","article-title":"DurIAN: Duration informed attention network for multimodal synthesis","author":"yu","year":"2019"},{"key":"ref10","article-title":"WaveFlow: A compact flow-based model for raw audio","author":"ping","year":"2020","journal-title":"Proc International Conference on Machine Learning"},{"key":"ref11","article-title":"MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis","author":"kumar","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"High Fidelity Speech Synthesis with Adversarial Networks","author":"bi?kowski","year":"2020","journal-title":"Proc International Conference on Learning Representations"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2880284"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682298"},{"key":"ref15","article-title":"A Spectral Energy Distance for Parallel Speech Synthesis","author":"gritsenko","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054484"},{"key":"ref17","article-title":"Flowtron: an autoregressive flow-based generative network for text-to-speech synthesis","author":"valle","year":"2020"},{"key":"ref18","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","author":"kim","year":"2020"},{"key":"ref19","article-title":"Fast-speech 2: Fast and high-quality end-to-end text-to-speech","author":"ren","year":"2020"},{"key":"ref28","first-page":"2175","article-title":"RNADE: The real-valued neural autoregressive density-estimator","author":"uria","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016"},{"key":"ref27","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"Char2Wav: End-to-end speech synthesis","author":"sotelo","year":"2017","journal-title":"Proc International Conference on Learning Representations"},{"key":"ref6","article-title":"Parallel WaveNet: Fast High-Fidelity Speech Synthesis","author":"van den oord","year":"2018","journal-title":"Proc International Conference on Machine Learning"},{"key":"ref29","article-title":"The LJ Speech Dataset","author":"ito","year":"2017"},{"key":"ref5","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"Proc International Conference on Machine Learning"},{"key":"ref8","article-title":"FloWaveNet: A generative flow for raw audio","author":"kim","year":"2019","journal-title":"Proc International Conference on Machine Learning"},{"key":"ref7","article-title":"ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech","author":"ping","year":"2019","journal-title":"Proc International Conference on Learning Representations"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref20","article-title":"End-to-end adversarial text-to-speech","author":"donahue","year":"2020"},{"key":"ref22","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref21","first-page":"1530","article-title":"Variational inference with normalizing flows","author":"rezende","year":"2015","journal-title":"Proc International Conference on Machine Learning"},{"key":"ref24","article-title":"NICE: Non-linear independent components estimation","author":"dinh","year":"2015","journal-title":"Proc International Conference on Learning Representations"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054106"},{"key":"ref26","article-title":"Density estimation using Real NVP","author":"dinh","year":"2017","journal-title":"Proc International Conf on Learning Representations"},{"key":"ref25","first-page":"10215","article-title":"Glow: Generative flow with invertible 1x1 convolutions","author":"kingma","year":"2018","journal-title":"Advances in neural information processing systems"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413851.pdf?arnumber=9413851","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:03Z","timestamp":1652197263000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413851\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413851","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}