{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T16:33:14Z","timestamp":1725726794355},"reference-count":34,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383549","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T16:46:54Z","timestamp":1616690814000},"page":"470-476","source":"Crossref","is-referenced-by-count":5,"title":["Improved Parallel Wavegan Vocoder with Perceptually Weighted Spectrogram Loss"],"prefix":"10.1109","author":[{"given":"Eunwoo","family":"Song","sequence":"first","affiliation":[]},{"given":"Ryuichi","family":"Yamamoto","sequence":"additional","affiliation":[]},{"given":"Min-Jae","family":"Hwang","sequence":"additional","affiliation":[]},{"given":"Jin-Seob","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Ohsung","family":"Kwon","sequence":"additional","affiliation":[]},{"given":"Jae-Min","family":"Kim","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"On the variance of the adaptive learning rate and beyond","year":"2019","author":"liu","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1984.1172448"},{"key":"ref31","first-page":"901","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","author":"salimans","year":"2016","journal-title":"Proc NIPS"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"CoRR"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.23915\/distill.00003","article-title":"Deconvolution and checkerboard artifacts","author":"odena","year":"2016","journal-title":"Distillation"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"article-title":"Parallel waveform synthesis based on generative adversarial networks with voicing-aware conditional discriminators","year":"2020","author":"yamamoto","key":"ref11"},{"key":"ref12","first-page":"14 881","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019","journal-title":"Proc NeurIPS"},{"article-title":"Multi-band MelGAN: Faster waveform generation for high-quality text-to-speech","year":"2020","author":"yang","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1238"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1121\/1.383662"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2880284"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461332"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1288"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2116"},{"article-title":"LP-WaveNet: Linear prediction-based WaveNet speech synthesis","year":"2018","author":"hwang","key":"ref4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003956"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"},{"key":"ref6","first-page":"3915","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","author":"van den oord","year":"2018","journal-title":"Proc ICML"},{"key":"ref29","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc AISTATS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8902701"},{"key":"ref8","first-page":"4743","article-title":"Improved variational inference with inverse autoregressive flow","author":"kingma","year":"2016","journal-title":"Proc NIPS"},{"key":"ref7","article-title":"ClariNet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"2019","journal-title":"Proc ICLR"},{"article-title":"WaveNet: A generative model for raw audio","year":"2016","author":"van den oord","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1965"},{"key":"ref1","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"Proc ICASSP"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-4"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"3642","DOI":"10.21437\/Interspeech.2017-1428","article-title":"SEGAN: Speech enhancement generative adversarial network","author":"pascual","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1288"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2746264"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2021,1,19]]},"location":"Shenzhen, China","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\/09383549.pdf?arnumber=9383549","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,3]],"date-time":"2021-05-03T17:40:16Z","timestamp":1620063616000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383549\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383549","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}