{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,13]],"date-time":"2025-09-13T15:44:24Z","timestamp":1757778264147,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095513","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Enhancement of Text-Predicting Style Token With Generative Adversarial Network for Expressive Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Hiroki","family":"Kanagawa","sequence":"first","affiliation":[{"name":"NTT Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusuke","family":"Ijima","sequence":"additional","affiliation":[{"name":"NTT Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"7748","article-title":"Meta-stylespeech : Multi-speaker adaptive text-to-speech generation","volume":"139","author":"min","year":"2021","journal-title":"Proc ICML"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2571"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10761"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-367"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"journal-title":"The guidelines for TTS speaking style classification (IT-4012)","year":"2021","key":"ref30"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref33","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref10","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume":"80","author":"wang","year":"2018","journal-title":"Proc ICML"},{"key":"ref32","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref2","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","author":"ping","year":"2018","journal-title":"Proc ICPE"},{"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":"Proc INTERSPEECH"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639682"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1129"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746883"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3074757"},{"key":"ref24","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2016","journal-title":"Proc ICLR"},{"key":"ref23","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc NIPS"},{"key":"ref26","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc NAACL-HLT"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2761547"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383629"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133205"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145293"},{"key":"ref28","article-title":"Variational discriminator bottleneck: Improving imitation learning, inverse rl, and gans by constraining information flow","author":"peng","year":"2019","journal-title":"Proc ICLR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461932"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref8","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282231"},{"key":"ref4","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2021","journal-title":"Proc ICPE"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref6","first-page":"2410","article-title":"Efficient Neural Audio Synthesis","volume":"80","author":"kalchbrenner","year":"2018","journal-title":"Proc ICML"},{"key":"ref5","article-title":"WaveNet: A generative model for raw audio","author":"den oord","year":"2016","journal-title":"CoRR abs\/1609 03499"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095513.pdf?arnumber=10095513","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:08:13Z","timestamp":1700507293000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095513\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095513","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}