{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T21:13:36Z","timestamp":1740172416181,"version":"3.37.3"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2018,4,1]],"date-time":"2018-04-01T00:00:00Z","timestamp":1522540800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program","doi-asserted-by":"crossref","award":["2016QY02D0401"],"award-info":[{"award-number":["2016QY02D0401"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"crossref","award":["U1636201"],"award-info":[{"award-number":["U1636201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["WK2350000001"],"award-info":[{"award-number":["WK2350000001"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/taslp.2018.2791804","type":"journal-article","created":{"date-parts":[[2018,1,10]],"date-time":"2018-01-10T20:54:33Z","timestamp":1515617673000},"page":"713-724","source":"Crossref","is-referenced-by-count":8,"title":["Extracting Spectral Features Using Deep Autoencoders With Binary Distributed Hidden Units for Statistical Parametric Speech Synthesis"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0624-6119","authenticated-orcid":false,"given":"Ya-Jun","family":"Hu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7853-5273","authenticated-orcid":false,"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","first-page":"3053","article-title":"Crowdsourcing preference tests, and how to detect cheating","author":"buchholz","year":"0","journal-title":"Proc INTERSPEECH"},{"year":"2001","key":"ref32","article-title":"Method for the subjective assessment of intermediate sound quality (MUSHRA)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758104"},{"key":"ref30","first-page":"2347","article-title":"Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis","volume":"6","author":"yoshimura","year":"0","journal-title":"Proc EUROSPEECH"},{"key":"ref10","first-page":"89","article-title":"Minimum generation error training for HMM-based speech synthesis","volume":"1","author":"wu","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2551865"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472749"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2461448"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472731"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953090"},{"article-title":"WaveNet: A generative model for raw audio","year":"2016","author":"van den oord","key":"ref16"},{"article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","year":"2016","author":"mehri","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-1.1.325"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref27","first-page":"926","article-title":"A practical guide to training restricted Boltzmann machines","volume":"9","author":"hinton","year":"2010","journal-title":"Momentum"},{"key":"ref3","first-page":"1692","article-title":"Binary coding of speech spectrograms using a deep auto-encoder","author":"deng","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639187"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"hinton","year":"2006","journal-title":"Science"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref8","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639225"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref9","first-page":"1964","article-title":"TTS synthesis with bidirectional LSTM based recurrent neural networks","author":"fan","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref20","article-title":"USTC system for Blizzard challenge 2006: An improved HMM-based speech synthesis method","author":"ling","year":"0","journal-title":"Proc Blizzard Challenge Workshop"},{"key":"ref22","article-title":"A function-wise pre-training technique for constructing a deep neural network based spectral model in statistical parametric speech synthesis","author":"takaki","year":"0","journal-title":"Proc 1st Int Conf Mach Learn Spoken Lang Process"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472736"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijar.2008.11.006"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2516032"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"journal-title":"Information Processing in Dynamical Systems Foundations of Harmony Theory","year":"1986","author":"smolensky","key":"ref25"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8271883\/08253499.pdf?arnumber=8253499","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:18:20Z","timestamp":1642004300000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8253499\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":33,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2018.2791804","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2018,4]]}}}