{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:21:21Z","timestamp":1778692881527,"version":"3.51.4"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61871358"],"award-info":[{"award-number":["61871358"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/taslp.2020.2970241","type":"journal-article","created":{"date-parts":[[2020,1,29]],"date-time":"2020-01-29T22:15:47Z","timestamp":1580336147000},"page":"839-851","source":"Crossref","is-referenced-by-count":27,"title":["A Neural Vocoder With Hierarchical Generation of Amplitude and Phase Spectra for Statistical Parametric Speech Synthesis"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6668-022X","authenticated-orcid":false,"given":"Yang","family":"Ai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7853-5273","authenticated-orcid":false,"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.5.816"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"ref33","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume":"30","author":"maas","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref32","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682298"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-33"},{"key":"ref36","first-page":"223","article-title":"The CMU Arctic speech databases","author":"kominek","year":"0","journal-title":"Proc ISCA Workshop"},{"key":"ref35","first-page":"3481","article-title":"Which training methods for GANs do actually converge?","author":"mescheder","year":"0","journal-title":"Proc ICML"},{"key":"ref34","first-page":"5767","article-title":"Improved training of Wasserstein GANs","author":"gulrajani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","author":"mehri","year":"0","journal-title":"Proc ICLR"},{"key":"ref40","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc ICLR"},{"key":"ref11","first-page":"2410","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"0","journal-title":"Proc ICML"},{"key":"ref12","article-title":"G. 711: Pulse code modulation (PCM) of voice frequencies","year":"1988","journal-title":"Int Telecommun Union"},{"key":"ref13","first-page":"3918","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","author":"oord","year":"0","journal-title":"Proc ICML"},{"key":"ref14","article-title":"ClariNet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"0","journal-title":"Proc ICLR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269007"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462393"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461878"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2906484"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2359987"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1635"},{"key":"ref3","first-page":"1964","article-title":"TTS synthesis with bidirectional LSTM based recurrent neural networks","author":"fan","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref29","article-title":"LP-WaveNet: Linear prediction-based WaveNet speech synthesis","author":"hwang","year":"2018"},{"key":"ref5","first-page":"122","article-title":"The vocoder","volume":"18","author":"dudley","year":"1939","journal-title":"Bell Labs Rec"},{"key":"ref8","article-title":"The acoustic theory of speech production","author":"gunnar","year":"1960"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref2","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"0","journal-title":"Proc 45th Int Conf Acoust Speech Signal Process"},{"key":"ref9","first-page":"125","article-title":"WaveNet: A generative model for raw audio","author":"oord","year":"2016","journal-title":"ISCA Workshop on Speech Synthesis"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683016"},{"key":"ref45","first-page":"3053","article-title":"Crowdsourcing preference tests, and how to detect cheating","author":"buchholz","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1190"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1424"},{"key":"ref42","article-title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems","author":"abadi","year":"2015"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2798811"},{"key":"ref41","article-title":"Pytorch: Tensors and dynamic neural networks in python with strong gpu acceleration","author":"paszke","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-986"},{"key":"ref44","first-page":"1543","article-title":"Method for the subjective assessment of intermediate sound quality (MUSHRA)","year":"2001","journal-title":"ITU BS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1757"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682298"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682435"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/08974251.pdf?arnumber=8974251","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:30:51Z","timestamp":1651080651000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8974251\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.2970241","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}