{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T01:59:12Z","timestamp":1729648752092,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462470","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"4799-4803","source":"Crossref","is-referenced-by-count":3,"title":["Cyborg Speech: Deep Multilingual Speech Synthesis for Generating Segmental Foreign Accent with Natural Prosody"],"prefix":"10.1109","author":[{"given":"Gustav Eje","family":"Henter","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaime","family":"Lorenzo-Trueba","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mariko","family":"Kondo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1177\/0261927X12463005"},{"key":"ref31","first-page":"1315","article-title":"Speech parameter generation algorithms for HMM-based speech synthesis","author":"keiichi","year":"2000","journal-title":"Proc ICASSP"},{"key":"ref30","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"john","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1121\/1.395275"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"2777","DOI":"10.21437\/Interspeech.2011-695","article-title":"Formant-controlled HMM-based speech synthesis","author":"lei","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref12","first-page":"1964","article-title":"TTS synthesis with bidirectional LSTM based recurrent neural networks","author":"fan","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref13","first-page":"4470","article-title":"Unidirectional long short-term memory recurrent neural network with recurrent output layer for low-latency speech synthesis","author":"heiga","year":"2015","journal-title":"Proc ICASSP"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472730"},{"key":"ref15","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"heiga","year":"2013","journal-title":"Proc ICASSP"},{"key":"ref16","first-page":"4905","article-title":"Adapting and controlling DNN-based speech synthesis using input codes","author":"hieu-thi","year":"2017","journal-title":"Proc ICASSP"},{"key":"ref17","first-page":"2217","article-title":"Sentence-level control vectors for deep neural network speech synthesis","author":"oliver","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref18","first-page":"3956","article-title":"Principles for learning controllable TTS from annotated and latent variation","author":"gustav","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-172"},{"key":"ref28","first-page":"4895","article-title":"An autoregressive recurrent mixture density network for parametric speech synthesis","author":"xin","year":"2017","journal-title":"Proc ICASSP"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1017\/S0272263101004016","article-title":"Modeling perceptions of the accentedness and comprehensibility of L2 speech","volume":"23","author":"munro","year":"2001","journal-title":"Stud Second Lang Acquis"},{"key":"ref27","first-page":"343","article-title":"Japanese text-to-speech synthesis system: Open JTalk","author":"keiichiro","year":"2010","journal-title":"Proc of spring conf of ASJ"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1006\/jpho.1996.0031"},{"key":"ref6","first-page":"1303","article-title":"Generating segmental foreign accent","author":"garc\u00eda lecumberri","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref29","first-page":"547","article-title":"Introducing CURRENNT: The Munich open-source CUDA recurrent neural network toolkit","volume":"16","author":"felix","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1017\/S0272263197001010","article-title":"Accent, intelligibility, and comprehensibility","volume":"19","author":"derwing","year":"1997","journal-title":"Stud Second Lang Acquis"},{"key":"ref8","article-title":"Perception and comprehension of synthetic speech","author":"winters","year":"0","journal-title":"Research on Spoken Language Processing Progress Report No 26 (2003–2004) 2004 Speech Research Laboratory"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/002383099203500401"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2307\/3588378"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1121\/1.383940"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-4781.2010.01091.x"},{"key":"ref20","first-page":"1059","article-title":"An RNN-based quantized F0 model with multi-tier feedback links for text-to-speech synthesis","author":"xin","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref22","first-page":"1877","article-title":"WORLD: A vocoder-based high-quality speech synthesis system for real-time applications","volume":"99","author":"masanori","year":"2016","journal-title":"IEICE -Trans Inf Syst"},{"key":"ref21","first-page":"1504","article-title":"Measuring the perceptual effects of modelling assumptions in speech synthesis using stimuli constructed from repeated natural speech","author":"gustav","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref24","first-page":"294","article-title":"The HMM-based speech synthesis system (HTS) version 2.0","author":"heiga","year":"2007","journal-title":"Proc of SSW6"},{"key":"ref23","article-title":"The NII speech synthesis entry for Blizzard Challenge 2016","author":"juvela","year":"2016","journal-title":"Proc Blizzard Challenge Workshop"},{"key":"ref26","first-page":"1295","article-title":"Robust LTS rules with the Combilex speech technology lexicon","author":"korin","year":"2009","journal-title":"Proc INTERSPEECH"},{"journal-title":"The English TTS system ‘Flite+hts_engine’","year":"2014","key":"ref25"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2018,4,15]]},"location":"Calgary, AB","end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08462470.pdf?arnumber=8462470","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,2]],"date-time":"2022-09-02T10:46:31Z","timestamp":1662115591000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462470\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462470","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}