{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:35:05Z","timestamp":1770917705985,"version":"3.50.1"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053337","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"6204-6208","source":"Crossref","is-referenced-by-count":10,"title":["Gaussian Lpcnet for Multisample Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Vadim","family":"Popov","sequence":"first","affiliation":[]},{"given":"Mikhail","family":"Kudinov","sequence":"additional","affiliation":[]},{"given":"Tasnima","family":"Sadekova","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"2410","article-title":"Efficient Neural Audio Synthesis","author":"kalchbrenner","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462431"},{"key":"ref12","article-title":"ExcitNet vocoder: A neural excitation model for parametric speech synthesis systems","author":"song","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2008"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1288","article-title":"Generative Adversarial Network-Based Glottal Waveform Model for Statistical Parametric Speech Synthesis","author":"bollepalli","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1705"},{"key":"ref17","author":"huang","year":"2001","journal-title":"Spoken Language Processing A Guide to Theory Algorithm and System Development"},{"key":"ref18","author":"moore","year":"2012","journal-title":"An Introduction to the Psychology of Hearing"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref4","first-page":"125","article-title":"WaveNet: A Generative Model for Raw Audio","author":"van den oord","year":"2016","journal-title":"ISCA Workshop on Speech Synthesis"},{"key":"ref3","article-title":"FastSpeech: Fast, Robust and Controllable Text to Speech","volume":"abs 1905 9263","author":"ren","year":"2019","journal-title":"ArXiv"},{"key":"ref6","article-title":"ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech","volume":"abs 1807 7281","author":"ping","year":"2018","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461332"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref7","first-page":"3918","article-title":"Parallel WaveNet: Fast High-Fidelity Speech Synthesis","author":"van den oord","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref2","article-title":"Neural Speech Synthesis with Transformer Network","author":"li","year":"2018","journal-title":"AAAI"},{"key":"ref9","first-page":"4743","article-title":"Improved Variational Inference with Inverse Autoregressive Flow","author":"kingma","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref20","article-title":"SampleRNN: An Unconditional End-to-End Neural Audio Generation Model","volume":"abs 1612 7837","author":"mehri","year":"2016","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1500"},{"key":"ref21","article-title":"The LJ Speech Dataset","author":"ito","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-21617-1"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053337.pdf?arnumber=9053337","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:11:03Z","timestamp":1656375063000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053337\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053337","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}