{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T06:34:57Z","timestamp":1777617297871,"version":"3.51.4"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2016,7,1]],"date-time":"2016-07-01T00:00:00Z","timestamp":1467331200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/3.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council Program","doi-asserted-by":"publisher","award":["EP\/I031022\/1"],"award-info":[{"award-number":["EP\/I031022\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Speech Technology"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2016,7]]},"DOI":"10.1109\/taslp.2016.2551865","type":"journal-article","created":{"date-parts":[[2016,4,7]],"date-time":"2016-04-07T15:47:28Z","timestamp":1460044048000},"page":"1255-1265","source":"Crossref","is-referenced-by-count":23,"title":["Improving Trajectory Modelling for DNN-Based Speech Synthesis by Using Stacked Bottleneck Features and Minimum Generation Error Training"],"prefix":"10.1109","volume":"24","author":[{"given":"Zhizheng","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"King","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"A practical guide to training restricted Boltzmann machines","author":"hinton","year":"2010"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref33","first-page":"227","article-title":"An HMM-based speech synthesis system applied to english","author":"tokuda","year":"0","journal-title":"Proc IEEE Workshop Speech Synthesis"},{"key":"ref32","article-title":"Investigating gated recurrent neural networks for speech synthesis","author":"wu","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"ref30","first-page":"1964","article-title":"TTS synthesis with bidirectional LSTM based recurrent neural networks","author":"fan","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"ref36","first-page":"2283","article-title":"Sequence error (SE) minimization training of neural network for voice conversion","author":"xie","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref35","first-page":"864","article-title":"Sequence generation error (SGE) minimization based deep neural networks training for text-to-speech synthesis","author":"fan","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref34","first-page":"309","article-title":"Minimum trajectory error training for deep neural networks, combined with stacked bottleneck features","author":"wu","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref28","first-page":"869","article-title":"Towards minimum perceptual error training for DNN-based speech synthesis","author":"valentini-botinhao","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref27","article-title":"A reading list of recent advances in speech synthesis","author":"king","year":"0","journal-title":"Proc 18th Int Congr Phon Sci"},{"key":"ref29","first-page":"854","article-title":"Fusion of multiple parameterisations for DNN-based sinusoidal speech synthesis with multi-task learning","author":"hu","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3989\/loquens.2014.006"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178815"},{"key":"ref22","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":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2461448"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854318"},{"key":"ref23","first-page":"281","article-title":"Combining a vector space representation of linguistic context with a deep neural network for text-to-speech synthesis","author":"lu","year":"0","journal-title":"Proc 8th Int Speech Commun Assoc Speech Synthesis Workshop"},{"key":"ref26","article-title":"From HMMs to DNNs: Where do the improvements come from","author":"watts","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178814"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2359987"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.675495"},{"key":"ref40","first-page":"426","article-title":"A perceptual study of acceleration parameters in HMM-based TTS","author":"chen","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298824"},{"key":"ref13","first-page":"291","article-title":"LSP speech synthesis using backpropagation networks","author":"cawley","year":"0","journal-title":"Proc 3rd Int Conf Artif Neural Netw"},{"key":"ref14","first-page":"4","article-title":"Speech synthesis using artificial neural networks trained on cepstral coefficients","author":"tuerk","year":"0","journal-title":"Proc Eur Conf Speech Commun Technol"},{"key":"ref15","first-page":"599","article-title":"A neural-network-based model of segmental duration for speech synthesis","author":"riedi","year":"0","journal-title":"Proc Eur Conf Speech Commun Technol"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2269291"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639225"},{"key":"ref18","first-page":"1959","article-title":"Statistical parametric speech synthesis using weighted multi-distribution deep belief network","author":"kang","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854321"},{"key":"ref4","first-page":"89","article-title":"Minimum generation error training for HMM-based speech synthesis","author":"wu","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.5.816"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2006.01.002"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178766"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853604"},{"key":"ref49","article-title":"Deep neural network-guided unit selection synthesis","author":"merritt","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref48","first-page":"2207","article-title":"Deep neural network context embeddings for model selection in rich-context HMM synthesis","author":"merritt","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518713"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178813"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288833"},{"key":"ref43","first-page":"237","article-title":"Improved bottleneck features using pretrained deep neural networks","author":"yu","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/ieeexplore.ieee.org\/iel7\/6570655\/7466869\/07448877.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7466869\/07448877.pdf?arnumber=7448877","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:42:05Z","timestamp":1641987725000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7448877\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,7]]},"references-count":49,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2016.2551865","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,7]]}}}