{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T14:21:46Z","timestamp":1762006906892,"version":"build-2065373602"},"reference-count":33,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8461332","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"5664-5668","source":"Crossref","is-referenced-by-count":27,"title":["An Investigation of Noise Shaping with Perceptual Weighting for Wavenet-Based Speech Generation"],"prefix":"10.1109","author":[{"given":"Kentaro","family":"Tachibana","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\/ASRU.2017.8269005"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1672"},{"key":"ref31","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":"ref30","doi-asserted-by":"crossref","first-page":"1138","DOI":"10.21437\/Interspeech.2017-986","article-title":"Statis-tical voice conversion with WaveNet-based waveform generation","author":"kobayashi","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269007"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"journal-title":"Samplernn An unconditional end-to-end neural audio generation model","year":"2016","author":"mehri","key":"ref13"},{"key":"ref14","article-title":"Char2wav: end-to-end speech synthesis","author":"sotelo","year":"2017","journal-title":"Proc ICLR"},{"journal-title":"Deep Voice Real-time neural text-to-speech","year":"2017","author":"arik","key":"ref15"},{"journal-title":"Deep voice 2 Multi-speaker neural text-to-speech","year":"2017","author":"arik","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1121\/1.383662"},{"key":"ref18","first-page":"141","article-title":"Predictive coding of speech using analysis by-synthesis techniques","author":"kroon","year":"1992","journal-title":"Advances in Speech Signal Processing"},{"journal-title":"Conditional image generation with pixelcnn decoders","year":"2016","author":"van den oord","key":"ref19"},{"journal-title":"Adam A method for stochastic optimization","year":"2014","author":"kingma","key":"ref28"},{"journal-title":"WaveNet A Generative Model for Raw Audio","year":"2016","author":"van den oord","key":"ref4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.09.001"},{"key":"ref3","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"Proc ICASSP"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-522"},{"journal-title":"Fast WaveNet generation algorithm","year":"2016","author":"le paine","key":"ref29"},{"journal-title":"Pulse Code Modulation (PCM) of Voice Frequencies","year":"1988","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1107"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-264"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref9","first-page":"1118","article-title":"Speaker-dependent WaveNet vocoder","author":"tamamori","year":"2017","journal-title":"Proc Inter-speech"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","first-page":"1043","article-title":"Mel-generalized cepstral analysis-a unified approach to speech spectral estimation","author":"tokukda","year":"1994","journal-title":"Proc ICSLP"},{"key":"ref21","first-page":"247","article-title":"Predictive coding of speech signals and subjective error criteria","author":"atal","year":"1978","journal-title":"Proc ICASSP"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90011-W"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225953"},{"key":"ref26","first-page":"495","article-title":"A robust algorithm for pitch tracking (RAPT)","author":"talkin","year":"1995","journal-title":"Speech Coding and Synthesis"},{"journal-title":"SWIPE A sawtooth waveform inspired pitch estimator for speech and music","year":"2007","author":"camacho","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\/08461332.pdf?arnumber=8461332","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T01:08:08Z","timestamp":1598231288000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461332\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8461332","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}