{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:37:35Z","timestamp":1730230655267,"version":"3.28.0"},"reference-count":20,"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\/icassp39728.2021.9413669","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"8593-8597","source":"Crossref","is-referenced-by-count":3,"title":["The Thinkit System for Icassp2021 M2voc Challenge"],"prefix":"10.1109","author":[{"given":"Zengqiang","family":"Shang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haozhe","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bolin","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengyuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Adadurian: Few-shot adaptation for neural text-to-speech with durian","author":"zhang","year":"2020","journal-title":"arXiv preprint arXiv 2005 06138"},{"key":"ref11","article-title":"Neural voice cloning with a few samples","author":"arik","year":"2018","journal-title":"arXiv preprint arXiv 1802 06360"},{"key":"ref12","article-title":"Aishell-3: A multi-speaker mandarin tts corpus and the baselines","author":"shi","year":"2020","journal-title":"arXiv preprint arXiv 2010 11567"},{"journal-title":"Speaker adaptation in dnn-based speech synthesis using d-vectors","year":"2017","author":"doddipatla","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3034994"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054301"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"498","DOI":"10.21437\/Interspeech.2017-1386","article-title":"Montreal forced aligner: Trainable text-speech alignment using kaldi","volume":"2017","author":"mcauliffe","year":"2017","journal-title":"InterSpeech"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682770"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2096"},{"key":"ref4","article-title":"Wavenet: A generative model for raw audio","author":"den oord","year":"2016","journal-title":"arXiv preprint arXiv 1609 04802"},{"key":"ref3","first-page":"3171","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref6","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"arXiv preprint arXiv 2010 00170"},{"key":"ref5","first-page":"14910","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019","journal-title":"Advances in neural information processing systems"},{"journal-title":"Towards achieving robust universal neural vocoding","year":"2019","author":"lorenzo-trueba","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2786"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref1","article-title":"The multi-speaker multi-style voice cloning challenge 2021","author":"xie","year":"2021","journal-title":"2021 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref9","article-title":"Sample efficient adaptive text-to-speech","author":"chen","year":"2018","journal-title":"arXiv preprint arXiv 1809 10460"},{"key":"ref20","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"arXiv preprint arXiv 1706 03762"}],"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\/09413669.pdf?arnumber=9413669","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:40:59Z","timestamp":1652182859000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413669\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413669","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}