{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T21:24:58Z","timestamp":1729632298670,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054490","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7784-7788","source":"Crossref","is-referenced-by-count":3,"title":["Lifter Training and Sub-Band Modeling for Computationally Efficient and High-Quality Voice Conversion Using Spectral Differentials"],"prefix":"10.1109","author":[{"given":"Takaaki","family":"Saeki","sequence":"first","affiliation":[]},{"given":"Yuki","family":"Saito","sequence":"additional","affiliation":[]},{"given":"Shinnosuke","family":"Takamichi","sequence":"additional","affiliation":[]},{"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"5916","article-title":"Neural source-filter-based waveform model for statistical parametric speech synthesis","author":"wang","year":"2018","journal-title":"Proc ICASSP"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/ecja.4400660203"},{"key":"ref12","first-page":"816","article-title":"A revisit to feature handling for high-quality voice conversion","author":"suda","year":"2018","journal-title":"Proc APSIPA ASC"},{"key":"ref13","first-page":"9","article-title":"Low-latency real-time blind source separation with binaural directional hearing aids","author":"sunohara","year":"2017","journal-title":"Proc CHATS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225953"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2006.882193"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"rumelhart","year":"1986","journal-title":"Nature"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269005"},{"article-title":"JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesis","year":"2017","author":"sonobe","key":"ref18"},{"article-title":"Voice-actress corpus","year":"0","author":"benjo","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960478"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-17"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"94","DOI":"10.21437\/Interspeech.2012-34","article-title":"Implementation of computationally efficient real-time voice conversion","author":"toda","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref8","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":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.03.011"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2014.7032186"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1988.196671"},{"article-title":"Efficient neural audio synthesis","year":"2018","author":"kalchbrenner","key":"ref9"},{"article-title":"JVS corpus: free Japanese multi-speaker voice corpus","year":"2019","author":"takamichi","key":"ref20"},{"article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","year":"2015","author":"ioffe","key":"ref22"},{"article-title":"Language modeling with gated convolutional networks","year":"2016","author":"dauphin","key":"ref21"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref23"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054490.pdf?arnumber=9054490","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T19:29:46Z","timestamp":1696015786000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054490\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054490","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}