{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:06:44Z","timestamp":1780765604547,"version":"3.54.1"},"reference-count":25,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,4]]},"DOI":"10.1109\/icassp.2015.7178814","type":"proceedings-article","created":{"date-parts":[[2015,8,12]],"date-time":"2015-08-12T22:45:43Z","timestamp":1439419543000},"page":"4460-4464","source":"Crossref","is-referenced-by-count":137,"title":["Deep neural networks employing Multi-Task Learning and stacked bottleneck features for speech synthesis"],"prefix":"10.1109","author":[{"given":"Zhizheng","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cassia","family":"Valentini-Botinhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oliver","family":"Watts","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simon","family":"King","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Combining a vector space representation of linguistic context with a deep neural network for text-to-speech synthesis","author":"lu","year":"2013","journal-title":"Proceedings of 8th ISCA Workshop on Speech Synthesis"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854318"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_5"},{"key":"ref14","article-title":"TTS synthesis with bidirectional LSTM based recurrent neural networks","author":"fan","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639012"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-91","article-title":"Improved bottleneck features using pretrained deep neural networks","author":"yu","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref19","article-title":"Auto-encoder bottleneck features using deep belief networks","author":"tara","year":"2012","journal-title":"Proc IEEE Int Conf on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref4","article-title":"Minimum generation error training for HMM-based speech synthesis","author":"wu","year":"2006","journal-title":"Proc IEEE Int Conf on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2006.01.002"},{"key":"ref5","first-page":"816","article-title":"A speech parameter generation algorithm considering global variance for HMM-based speech synthesis","volume":"90","author":"tomoki","year":"2007","journal-title":"IEICE Transactions on Information and Systems"},{"key":"ref8","article-title":"Multidistribution deep belief network for speech synthesis","author":"kang","year":"2013","journal-title":"Proc IEEE Int Conf on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref7","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"Proc IEEE Int Conf on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3989\/loquens.2014.006"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2269291"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref20","article-title":"Extracting deep bottleneck features using stacked autoencoders","author":"gehring","year":"0","journal-title":"Proc IEEE Int Conf on Acoustics Speech and Signal Processing (ICASSP) 2013"},{"key":"ref22","article-title":"Gammatone-like spectrograms","author":"ellis","year":"2009"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.25080\/Majora-92bf1922-003","article-title":"Theano: a CPU and GPU math expression compiler","author":"bergstra","year":"2010","journal-title":"Proceedings of the Python for Scientific Computing Conference (SciPy)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/S0095-4470(03)00013-5"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854321"}],"event":{"name":"ICASSP 2015 - 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"South Brisbane, Queensland, Australia","start":{"date-parts":[[2015,4,19]]},"end":{"date-parts":[[2015,4,24]]}},"container-title":["2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7158221\/7177909\/07178814.pdf?arnumber=7178814","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,20]],"date-time":"2022-05-20T09:39:05Z","timestamp":1653039545000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7178814\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,4]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp.2015.7178814","relation":{},"subject":[],"published":{"date-parts":[[2015,4]]}}}