{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T07:29:34Z","timestamp":1768980574214,"version":"3.49.0"},"reference-count":21,"publisher":"IEEE","license":[{"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\/icassp40776.2020.9054582","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T16:21:13Z","timestamp":1586449273000},"page":"3277-3281","source":"Crossref","is-referenced-by-count":28,"title":["Singing Voice Conversion with Disentangled Representations of Singer and Vocal Technique Using Variational Autoencoders"],"prefix":"10.1109","author":[{"given":"Yin-Jyun","family":"Luo","sequence":"first","affiliation":[{"name":"Singapore University of Technology and Design"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chin-Cheng","family":"Hsu","sequence":"additional","affiliation":[{"name":"University of Southern California,Los Angeles,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kat","family":"Agres","sequence":"additional","affiliation":[{"name":"A*STAR,Institute of High Performance Computing,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dorien","family":"Herremans","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Hierarchical generative modeling for controllable speech synthesis","author":"hsu","year":"2019","journal-title":"ICLRE"},{"key":"ref11","article-title":"Learning disentangled representations of timbre and pitch for musical instrument sounds using gaussian mixture variational autoencoders","author":"luo","year":"2019","journal-title":"ISMIR"},{"key":"ref12","first-page":"468","article-title":"Vocalset: A singing voice dataset","author":"wilkins","year":"2018","journal-title":"ISMIR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-21233-3_6"},{"key":"ref14","article-title":"Feed-forward networks with attention can solve some long-term memory problems","author":"raffel","year":"2016","journal-title":"ICLR Workshop Track"},{"key":"ref15","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"ICLRE"},{"key":"ref16","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"AISTATS"},{"key":"ref17","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"key":"ref18","first-page":"4869","author":"sun","year":"2015","journal-title":"ICASSP"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref4","author":"nachmani","year":"2019","journal-title":"Unsupervised singing voice conversion"},{"key":"ref3","article-title":"Statistical singing voice conversion with direct waveform modification based on the spectrum differential","author":"kobayashi","year":"2014","journal-title":"InterSpeech"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR.2019.00059"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/273"},{"key":"ref7","author":"dilokthanakul","year":"2016","journal-title":"Deep unsupervised clustering with gaussian mixture variational autoencoders"},{"key":"ref2","first-page":"1","article-title":"Singing voice conversion method based on many-tomany eigenvoice conversion and training data generation using a singing-to-singing synthesis system","author":"doi","year":"2012","journal-title":"APSIPA"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-596","article-title":"Applying voice conversion to concatenative singing-voice synthesis","author":"villavicencio","year":"2010","journal-title":"InterSpeech"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023162"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref21","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"ganin","year":"2016","journal-title":"The Journal of Machine Learning Research"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"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\/09054582.pdf?arnumber=9054582","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T15:29:02Z","timestamp":1696001342000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054582\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054582","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}