{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T15:51:07Z","timestamp":1778860267365,"version":"3.51.4"},"reference-count":25,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1109\/iwaenc.2018.8521313","type":"proceedings-article","created":{"date-parts":[[2018,11,6]],"date-time":"2018-11-06T02:38:56Z","timestamp":1541471936000},"page":"286-290","source":"Crossref","is-referenced-by-count":38,"title":["Phase Reconstruction from Amplitude Spectrograms Based on Von-Mises-Distribution Deep Neural Network"],"prefix":"10.1109","author":[{"given":"Shinnosuke","family":"Takamichi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Saito","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Norihiro","family":"Takamune","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daichi","family":"Kitamura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"Proc ICASSP"},{"key":"ref11","first-page":"309","article-title":"Minimum trajectory error training for deep neural networks, combined with stacked bottleneck features","author":"wu","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178813"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316979"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1049\/cp:19950550"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1987.1169476"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"2355","DOI":"10.21437\/Interspeech.2009-397","article-title":"Robustness of phase based features for speaker recognition","author":"padmanabhan","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1198\/016214505000000286"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s00362-009-0277-x"},{"key":"ref19","volume":"abs 1711 354","author":"sonobe","year":"2017","journal-title":"JSUT corpus free large-scale japanese speech corpus for end-to-end speech synthesis"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461714"},{"key":"ref3","volume":"abs 1609 3499","author":"wang","year":"2017","journal-title":"Tacotron Towards end-to-end speech synthesis"},{"key":"ref6","first-page":"2672","article-title":"Generative ad-versarial nets","author":"goodfellow","year":"2014","journal-title":"Proc NIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref8","first-page":"1718","article-title":"Generative moment matching networks","author":"li","year":"2015","journal-title":"Proc ICML"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2761547"},{"key":"ref2","article-title":"Direct modeling of frequency spectra and waveform generation based on phase recovery for DNN-based speech synthesis","author":"takaki","year":"2017","journal-title":"Proc Inter-speech"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-362"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref20","volume":"abs 1612 8083","author":"dauphin","year":"2016","journal-title":"Lan-guage modeling with gated convolutional networks"},{"key":"ref22","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume":"30","author":"maas","year":"2013","journal-title":"Proc ICML"},{"key":"ref21","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"2011","journal-title":"Proc AISTATS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/89.890068"},{"key":"ref23","first-page":"2121","article-title":"Adaptive sub gradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"EURASIP Journal on Applied Signal Processing"},{"key":"ref25","first-page":"177","article-title":"Signal reconstruction from STFT magnitude: A state of the art","author":"sturmel","year":"2011","journal-title":"Proc Int Conference of Digital Audio Effects DAFx"}],"event":{"name":"2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)","location":"Tokyo","start":{"date-parts":[[2018,9,17]]},"end":{"date-parts":[[2018,9,20]]}},"container-title":["2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8500052\/8521237\/08521313.pdf?arnumber=8521313","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T17:10:35Z","timestamp":1643217035000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8521313\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/iwaenc.2018.8521313","relation":{},"subject":[],"published":{"date-parts":[[2018,9]]}}}