{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T04:36:16Z","timestamp":1768970176129,"version":"3.49.0"},"reference-count":21,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746994","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"8302-8306","source":"Crossref","is-referenced-by-count":7,"title":["Improving Emotional Speech Synthesis by Using SUS-Constrained VAE and Text Encoder Aggregation"],"prefix":"10.1109","author":[{"given":"Fengyu","family":"Yang","sequence":"first","affiliation":[{"name":"Xiaomi Corporation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Luan","sequence":"additional","affiliation":[{"name":"Xiaomi Corporation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujun","family":"Wang","sequence":"additional","affiliation":[{"name":"Xiaomi Corporation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2423"},{"key":"ref12","article-title":"Bidirectional variational inference for non-autoregressive text-to-speech","author":"lee","year":"2021","journal-title":"Proc ICLR"},{"key":"ref13","article-title":"Vara-tts: Non-autoregressive text-to-speech synthesis based on very deep vae with residual attention","author":"liu","year":"2021","journal-title":"arXiv 2102 06431"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054106"},{"key":"ref15","first-page":"2415","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"Proc ICML"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref17","first-page":"3165","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2167"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023186"},{"key":"ref3","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"Proc ICML"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053732"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2931673"},{"key":"ref8","article-title":"Autoencoding variational bayes","author":"kingma","year":"2014","journal-title":"Proc ICLR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413398"},{"key":"ref2","article-title":"Emotional end-to-end neural speech synthesizer","author":"lee","year":"2017","journal-title":"arXiv 1711 05447"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.03.002"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1113"},{"key":"ref20","article-title":"Visualizing data using t-sne","volume":"9","author":"der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref21","article-title":"Generating diverse and natural text-to-speech samples using a quantized fine-grained vae and auto-regressive prosody prior","author":"sun","year":"2020","journal-title":"arXiv preprint arXiv 2002 05155"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"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\/09746994.pdf?arnumber=9746994","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:13:30Z","timestamp":1661199210000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746994\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746994","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}