{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:32:22Z","timestamp":1730230342583,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414220","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6583-6587","source":"Crossref","is-referenced-by-count":1,"title":["Unsupervised Learning for Multi-Style Speech Synthesis with Limited Data"],"prefix":"10.1109","author":[{"given":"Shuang","family":"Liang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenfeng","family":"Miao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minchuan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaojun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"ICML"},{"key":"ref11","article-title":"A generative adversarial network for style modeling in a text-to-speech system","author":"ma","year":"2019","journal-title":"ICLRE"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.21437\/Interspeech.2017-349","article-title":"Learning latent representations for speech generation and transformation","author":"hsu","year":"2017","journal-title":"InterSpeech"},{"key":"ref13","article-title":"Hierarchical generative modeling for controllable speech synthesis","author":"hsu","year":"2019","journal-title":"ICLRE"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/ICASSP.2019.8683623"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.21437\/Interspeech.2018-1113"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ICASSP40776.2020.9053678"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/ICASSP40776.2020.9053436"},{"key":"ref18","first-page":"3693","article-title":"Adjusting pleasure-arousal-dominance for continuous emotional text-to-speech synthesizer","author":"rabiee","year":"2019","journal-title":"InterSpeech"},{"key":"ref19","first-page":"4480","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018","journal-title":"NeurIPS"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ICASSP40776.2020.9054484"},{"key":"ref27","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref3","article-title":"Close to human quality TTS with transformer","author":"li","year":"2019","journal-title":"AAAI"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref5","first-page":"125","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"9th ISCA Speech Synthesis Workshop"},{"key":"ref8","first-page":"14910","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019","journal-title":"NeurIPS"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/ICASSP.2019.8682804"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref9","article-title":"Emotional end-to-end neural speech synthesizer","author":"lee","year":"2017","journal-title":"NeurIPS"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"InterSpeech"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/APSIPAASC47483.2019.9023186"},{"key":"ref22","first-page":"530","article-title":"Mutual information neural estimation","author":"belghazi","year":"2018","journal-title":"ICML"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/ICASSP40776.2020.9054591"},{"key":"ref24","article-title":"Deep variational information bottleneck","author":"alemi","year":"2017","journal-title":"ICLRE"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/CVPR.2018.00393"},{"year":"2012","author":"yamagishi","article-title":"English multi-speaker corpus for cstrvoice cloning toolkit","key":"ref26"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/ICASSP.2018.8462020"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414220.pdf?arnumber=9414220","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:48Z","timestamp":1652197248000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414220\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414220","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}