{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T06:01:12Z","timestamp":1774159272467,"version":"3.50.1"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,7]]},"DOI":"10.1109\/ijcnn.2019.8852253","type":"proceedings-article","created":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T03:44:32Z","timestamp":1569901472000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["RNN-based speech synthesis using a continuous sinusoidal model"],"prefix":"10.1109","author":[{"given":"Mohammed Salah","family":"Al-Radhi","sequence":"first","affiliation":[]},{"given":"Tamas","family":"Gabor Csapo","sequence":"additional","affiliation":[]},{"given":"Geza","family":"Nemeth","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947580"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"2781","DOI":"10.21437\/Eurospeech.1999-613","article-title":"Fixed point analysis of frequency to instantaneous frequency mapping for accurate estimation of f0 and periodicity","author":"kawahara","year":"1999","journal-title":"Proceedings of the Eurospeech"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.1993.342411"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_2"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178900"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"382","DOI":"10.21437\/Interspeech.2012-138","article-title":"A Full-Band Adaptive Harmonic Representation of Speech","author":"degottex","year":"2012","journal-title":"Proceedings of Interspeech"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-36"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362334"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-382"},{"key":"ref34","first-page":"423","article-title":"The IF spectrogram: a new spectral representation","volume":"97","author":"abe","year":"1997","journal-title":"Proc ASVA"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66429-3_27"},{"key":"ref27","article-title":"Continuous vocoder in feed-forward deep neural network based speech synthesis","author":"al-radhi","year":"2017","journal-title":"Proceedings of digital speech and image processing"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"451","DOI":"10.21437\/Eurospeech.1995-122","article-title":"High-quality speech modification based on a harmonic + noise model","author":"stylianou","year":"1995","journal-title":"Proceedings of EUROSPEECH"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"2347","DOI":"10.21437\/Eurospeech.1999-513","article-title":"Simultaneous modeling of spectrum, pitch, and duration in HMM based speech synthesis","author":"yoshimura","year":"1999","journal-title":"Proceedings of EUROSPEECH"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1016\/j.specom.2009.04.004","article-title":"Statistical parameteric speech synthesis","volume":"51","author":"zen","year":"2009","journal-title":"Speech Communication"},{"key":"ref20","first-page":"1","article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","author":"mehri","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"ref22","first-page":"155","article-title":"An experimental comparison of multiple vocoder types","author":"hu","year":"2013","journal-title":"Proc ISCA S"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2231675"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25789-1_4"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-678"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2332186"},{"key":"ref50","article-title":"Methods for the calculation of the speech intelligibility index","year":"1997"},{"key":"ref51","article-title":"Method for the subjective assessment of intermediate audio quality","year":"2001"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960478"},{"key":"ref11","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"Proceedings of ICASSP"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1109\/TASSP.1981.1163506","article-title":"Some windows with very good sidelobe behavior","volume":"29","author":"nuttall","year":"1981","journal-title":"IEEE Trans on Acoust Speech and Signal Processing"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2015.10.007"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178814"},{"key":"ref14","first-page":"2242","article-title":"Multiple feed-forward deep neural networks for statistical parametric speech synthesis","author":"takaki","year":"2015","journal-title":"Proceedings of Interspeech"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref18","first-page":"1964","article-title":"TTS synthesis with bidirectional LSTM based recurrent neural networks","author":"fan","year":"2014","journal-title":"Proceedings of Interspeech"},{"key":"ref19","article-title":"WaveNet: A Generative Model for Raw Audio","author":"oord","year":"2016","journal-title":"Proceedings of Speech Synthesis Workshop 9 (SSW9)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2359987"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861820"},{"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","first-page":"45","article-title":"Speech synthesis with neural networks","author":"karaali","year":"1996","journal-title":"Proceedings of World Congress on Neural Networks"},{"key":"ref7","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":"ref49","doi-asserted-by":"publisher","DOI":"10.1121\/1.3097493"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"ref46","author":"kominek","year":"2003","journal-title":"CMU ARCTIC Databases for Speech Synthesis"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1250\/ast.39.263"},{"key":"ref48","author":"quackenbush","year":"1988","journal-title":"Objective Measures of Speech Quality"},{"key":"ref47","article-title":"Merlin: An Open Source Neural Network Speech Synthesis System","author":"zhizheng","year":"2016","journal-title":"9th ISCA Speech Synthesis Workshop (SSW9)"},{"key":"ref42","author":"kominek","year":"2003","journal-title":"CMU ARCTIC Databases for Speech Synthesis"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1966.tb01706.x"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2013.2283471"}],"event":{"name":"2019 International Joint Conference on Neural Networks (IJCNN)","location":"Budapest, Hungary","start":{"date-parts":[[2019,7,14]]},"end":{"date-parts":[[2019,7,19]]}},"container-title":["2019 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8840768\/8851681\/08852253.pdf?arnumber=8852253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T16:28:20Z","timestamp":1664555300000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8852253\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2019.8852253","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}