{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:30:26Z","timestamp":1763202626608,"version":"3.37.3"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746875","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"4293-4297","source":"Crossref","is-referenced-by-count":18,"title":["nnSpeech: Speaker-Guided Conditional Variational Autoencoder for Zero-Shot Multi-speaker text-to-speech"],"prefix":"10.1109","author":[{"given":"Botao","family":"Zhao","sequence":"first","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xulong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianzong","family":"Wang","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ning","family":"Cheng","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Xiao","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Neural voice cloning with a few samples","author":"arik","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1737"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref13","first-page":"7748","article-title":"Meta-stylespeech: Multi-speaker adaptive text-to-speech generation","author":"min","year":"2021","journal-title":"ICML"},{"key":"ref14","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1632"},{"key":"ref16","article-title":"Learning structured output representation using deep conditional generative models","author":"sohn","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1061"},{"key":"ref18","first-page":"121","article-title":"Stochastic gradient vb and the variational auto-encoder","author":"kingma","year":"2017","journal-title":"ICLRE"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref4","article-title":"Hifigan: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"ADVANCES IN NEURAL IN-FORMATION PROCESSING SYSTEMS"},{"key":"ref3","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020","journal-title":"ICLRE"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2530"},{"key":"ref5","first-page":"1","article-title":"CycleGEAN:cycle generative enhanced adversarial network for voice conversion","author":"zhang","year":"2021","journal-title":"ASRU"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1705"},{"key":"ref7","article-title":"Adaspeech: Adaptive text to speech for custom voice","author":"chen","year":"2021","journal-title":"ICLRE"},{"key":"ref2","first-page":"3165","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"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"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054301"},{"key":"ref20","first-page":"1526","article-title":"Lib-ritts: A corpus derived from librispeech for text-to-speech","author":"zen","year":"2019","journal-title":"InterSpeech"},{"article-title":"The lj speech dataset","year":"2017","author":"ito","key":"ref22"},{"key":"ref21","article-title":"Aishell-3: A multi-speaker mandarin tts corpus and the baselines","author":"shi","year":"2020","journal-title":"arXiv preprint arXiv 2010 11567"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746875.pdf?arnumber=9746875","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:07:51Z","timestamp":1660594071000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746875\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746875","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}