{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:23:44Z","timestamp":1753601024952,"version":"3.28.0"},"reference-count":63,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/slt.2018.8639687","type":"proceedings-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T18:36:34Z","timestamp":1550169394000},"page":"304-311","source":"Crossref","is-referenced-by-count":8,"title":["Improving FFTNet Vocoder with Noise Shaping and Subband Approaches"],"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":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1528"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1131"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1506"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461960"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462393"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461452"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461948"},{"key":"ref36","first-page":"6306","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017","journal-title":"Proc NIPS"},{"key":"ref35","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":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1635"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-1.1.325"},{"journal-title":"ITU-T Recommendation P 800","article-title":"Methods for subjective determination of transmission quality","year":"1996","key":"ref62"},{"key":"ref61","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref63","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.21437\/Interspeech.2017-336","article-title":"Waveform modeling using stacked dilated convolutional neural networks for speech bandwidth extension","author":"gu","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"1118","DOI":"10.21437\/Interspeech.2017-314","article-title":"Speaker-dependent WaveNet vocoder","author":"tamamori","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref27","first-page":"5167","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"Proc ICML"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461878"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.01.008"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref20","first-page":"2415","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"Proc ICML"},{"key":"ref22","first-page":"195","article-title":"Deep voice: Real-time neural text-to-speech","author":"arik","year":"2017","journal-title":"Proc ICML"},{"key":"ref21","article-title":"Char2Wav: End-to-end speech synthesis","author":"sotelo","year":"2017","journal-title":"Proc ICLR"},{"key":"ref24","article-title":"Deep voice 3: 2000-speaker neural text-to-speech","author":"ping","year":"2018","journal-title":"Proc ICLR"},{"key":"ref23","first-page":"2966","article-title":"Deep voice 2: Multispeaker neural text-to-speech","author":"arik","year":"2017","journal-title":"Proc NIPS"},{"key":"ref26","first-page":"4700","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","author":"skerry-ryan","year":"2018","journal-title":"Proc ICML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163237"},{"key":"ref51","first-page":"1043","article-title":"Melgeneralized cepstral analysis — A unified approach to speech spectral estimation","author":"tokuda","year":"1994","journal-title":"Proc ICSLP"},{"key":"ref59","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":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1210"},{"key":"ref57","doi-asserted-by":"crossref","first-page":"1313","DOI":"10.3390\/app7121313","article-title":"A neural parametric singing synthesizer modeling timbre and expression from natural songs","volume":"7","author":"blaauw","year":"2017","journal-title":"Appl Sci"},{"key":"ref56","doi-asserted-by":"crossref","first-page":"4001","DOI":"10.21437\/Interspeech.2017-1420","article-title":"A neural parametric singing synthesizer","author":"blaauw","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref55","article-title":"PixelCNN++: Improving the pixelCNN with discretized logistic mixture likelihood and other modifications","author":"salimans","year":"2017","journal-title":"Proc ICLR"},{"key":"ref54","first-page":"4790","article-title":"Conditional image generation with pixelCNN decoders","author":"van den oord","year":"2016","journal-title":"Proc NIPS"},{"journal-title":"Multirate Systems and Filter Banks","year":"1993","author":"vaidyanathan","key":"ref53"},{"journal-title":"Multirate Digital Signal Processing","year":"1983","author":"crociere","key":"ref52"},{"key":"ref10","first-page":"2473","article-title":"GlottDNN — A full-band glottal vocoder for statistical parametric speech synthesis","author":"airaksinen","year":"2016","journal-title":"Proc INTERSPEECH"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2835720"},{"key":"ref40","first-page":"712","article-title":"An investigation of multi-speaker training for WaveNet vocoder","author":"hayashi","year":"2017","journal-title":"Proc ASRU"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1250\/ast.39.163"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-488"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2359987"},{"key":"ref17","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"arXiv preprint arXiv 1609 09861"},{"key":"ref18","first-page":"3915","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","author":"van den oord","year":"2018","journal-title":"Proc ICML"},{"key":"ref19","article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","author":"mehri","year":"2017","journal-title":"Proc ICLR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225953"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2673807"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178768"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2013.2283471"},{"journal-title":"ITU-T Recommendation G 711","article-title":"Pulse Code Modulation (PCM) of voice frequencies","year":"1988","key":"ref49"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472736"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269005"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2818408"},{"key":"ref48","article-title":"Fast generation for convolutional autoregressive models","author":"ramachandran","year":"2017","journal-title":"Proc ICLR"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462237"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462431"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461332"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"}],"event":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2018,12,18]]},"location":"Athens, Greece","end":{"date-parts":[[2018,12,21]]}},"container-title":["2018 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8632666\/8639030\/08639687.pdf?arnumber=8639687","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T00:49:34Z","timestamp":1643244574000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8639687\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/slt.2018.8639687","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}