{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:05:33Z","timestamp":1740099933705,"version":"3.37.3"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,24]],"date-time":"2021-01-24T00:00:00Z","timestamp":1611446400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,24]],"date-time":"2021-01-24T00:00:00Z","timestamp":1611446400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,24]],"date-time":"2021-01-24T00:00:00Z","timestamp":1611446400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,24]]},"DOI":"10.1109\/iscslp49672.2021.9362110","type":"proceedings-article","created":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T23:37:05Z","timestamp":1614641825000},"page":"1-5","source":"Crossref","is-referenced-by-count":6,"title":["Towards Fine-Grained Prosody Control for Voice Conversion"],"prefix":"10.1109","author":[{"given":"Zheng","family":"Lian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rongxiu","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengqi","family":"Wen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"IEEE Signal Processing Society Tech Rep"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2047683"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706604"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref14","first-page":"1","article-title":"Phonetic posteriorgrams for many-to-one voice conversion without parallel data training","author":"sun","year":"2016","journal-title":"IEEE International Conference on Multimedia and Expo (ICME)"},{"key":"ref15","first-page":"6790","article-title":"Cross-lingual voice conversion with bilingual phonetic posteriorgram and average modeling","author":"zhou","year":"2019","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref16","first-page":"6810","article-title":"A compact framework for voice conversion using wavenet conditioned on phonetic posteriorgrams","author":"lu","year":"2019","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1514"},{"key":"ref18","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","author":"skerry-ryan","year":"2018"},{"key":"ref19","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018"},{"key":"ref28","first-page":"9605","article-title":"An intriguing failing of convolutional neural networks and the coordconv solution","author":"liu","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref4","first-page":"3277","article-title":"Singing voice conversion with disentangled representations of singer and vocal technique using variational autoencoders","author":"luo","year":"2020","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref27","first-page":"457","article-title":"A hybrid approach to singing pitch extraction based on trend estimation and hidden markov models","author":"yeh","year":"2012","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref3","first-page":"7744","article-title":"End-to-end voice conversion via cross-modal knowledge distillation for dysarthric speech reconstruction","author":"wang","year":"2020","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041113"},{"key":"ref29","first-page":"5911","article-title":"Robust and fine-grained prosody control of end-to-end speech synthesis","author":"lee","year":"2019","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref5","first-page":"7749","article-title":"Pitchnet: Unsupervised singing voice conversion with pitch adversarial network","author":"deng","year":"2020","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref7","first-page":"7774","article-title":"Emotional voice conversion using multitask learning with text-to-speech","author":"kim","year":"2020","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1789"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1587\/transfun.E96.A.1946"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.05.001"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref22","first-page":"125","article-title":"Wavenet: A generative model for raw audio","author":"oord","year":"2016","journal-title":"The 9th ISCA Speech Synthesis Workshop"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref24","first-page":"5891","article-title":"Lpcnet: Improving neural speech synthesis through linear prediction","author":"valin","year":"2019","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref23","first-page":"2415","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"journal-title":"An Introduction to the Psychology of Hearing","year":"2012","author":"moore","key":"ref25"}],"event":{"name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2021,1,24]]},"location":"Hong Kong","end":{"date-parts":[[2021,1,27]]}},"container-title":["2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9362048\/9362049\/09362110.pdf?arnumber=9362110","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:57Z","timestamp":1652197317000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9362110\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,24]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/iscslp49672.2021.9362110","relation":{},"subject":[],"published":{"date-parts":[[2021,1,24]]}}}