{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T06:17:14Z","timestamp":1725603434881},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682320","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"7020-7024","source":"Crossref","is-referenced-by-count":5,"title":["Investigations of Real-time Gaussian Fftnet and Parallel Wavenet Neural Vocoders with Simple Acoustic Features"],"prefix":"10.1109","author":[{"given":"Takuma","family":"Okamoto","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshinori","family":"Shiga","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hisashi","family":"Kawai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682298"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"journal-title":"Methods for subjective determination of transmission quality","year":"1996","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461452"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1635"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1138","DOI":"10.21437\/Interspeech.2017-986","article-title":"Statistical voice conversion with WaveNet-based waveform generation","author":"kobayashi","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461948"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1528"},{"key":"ref15","first-page":"712","article-title":"An investigation of multi-speaker training for WaveNet vocoder","author":"hayashi","year":"2017","journal-title":"Proc ASRU"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461332"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269005"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462237"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639687"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"537","DOI":"10.21437\/Interspeech.2005-335","article-title":"Nearly defect-free F0 trajectory extraction for expressive speech modifications based on STRAIGHT","author":"kawahara","year":"2005","journal-title":"Proc INTERSPEECH"},{"key":"ref4","first-page":"2415","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"Proc ICML"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163237"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462431"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.01.008"},{"key":"ref29","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref8","first-page":"1118","article-title":"Speaker-dependent WaveNet vocoder","author":"tamamori","year":"2017","journal-title":"Proc In-terspeech"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref2","article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","author":"mehri","year":"2017","journal-title":"Proc ICLR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461878"},{"article-title":"WaveNet: A generative model for raw audio","year":"2016","author":"van den oord","key":"ref1"},{"key":"ref20","first-page":"3915","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","author":"van den oord","year":"2018","journal-title":"Proc ICML"},{"key":"ref22","article-title":"ClariNet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"2019","journal-title":"Proc ICLR"},{"key":"ref21","first-page":"4743","article-title":"Improved variational inference with inverse autoregressive flow","author":"kingma","year":"2016","journal-title":"Proc NIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225953"},{"key":"ref23","first-page":"1043","article-title":"Mel-generalized cepstral analysis — A unified approach to speech spectral estimation","author":"tokuda","year":"1994","journal-title":"Proc ICSLP"},{"journal-title":"Pulse Code Modulation (PCM) of Voice Frequencies","year":"1988","key":"ref26"},{"key":"ref25","article-title":"Fast generation for convolutional autoregressive models","author":"ramachandran","year":"2017","journal-title":"Proc ICLR"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, United Kingdom","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682320.pdf?arnumber=8682320","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,16]],"date-time":"2022-09-16T01:33:58Z","timestamp":1663292038000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682320\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682320","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}