{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:46:28Z","timestamp":1730231188931,"version":"3.28.0"},"reference-count":30,"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\/icassp49357.2023.10097113","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":["MID-Attribute Speaker Generation Using Optimal-Transport-Based Interpolation of Gaussian Mixture Models"],"prefix":"10.1109","author":[{"given":"Aya","family":"Watanabe","sequence":"first","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinnosuke","family":"Takamichi","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Saito","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Detai","family":"Xin","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.07.001"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413880"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747345"},{"key":"ref14","article-title":"Flowtron: An autoregressive flow-based generative network for text-to-speech synthesis","author":"valle","year":"2021","journal-title":"Proc ICLR"},{"journal-title":"Japanese Speech Database Read by Foreign Students (UME-JRF)","year":"0","key":"ref30"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1774"},{"key":"ref2","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":"ref1","first-page":"125","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"Proc SSW"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1137\/100805741"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.06.003"},{"journal-title":"Topics in Optimal Transportation","year":"2003","author":"villani","key":"ref19"},{"key":"ref18","first-page":"199","article-title":"On the translocation of masses (in Russian)","volume":"37","author":"kantorovich","year":"1942","journal-title":"USSR Academy of Sciences"},{"key":"ref24","first-page":"1005","article-title":"Wasserstein geometry of Gaussian measures","volume":"48","author":"takatsu","year":"2011","journal-title":"Osaka J Math"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-71050-9"},{"article-title":"Superseded-CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","year":"2016","author":"veaux","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1250\/ast.41.761"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2889838"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1081\/PDE-100002243"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1137\/S0036141096303359"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-897"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref29","first-page":"17 022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"kong","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref8","article-title":"AdaSpeech: Adaptive text to speech for custom voice","author":"chen","year":"2021","journal-title":"Proc ICLR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054301"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2096"},{"key":"ref4","first-page":"2966","article-title":"Deep Voice 2: Multi-speaker neural text-to-speech","volume":"30","author":"gibiansky","year":"2017","journal-title":"Proc NIPS"},{"key":"ref3","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2021","journal-title":"Proc ICLR"},{"key":"ref6","first-page":"4480","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume":"31","author":"jia","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref5","first-page":"10 019","article-title":"Neural voice cloning with a few samples","volume":"31","author":"arik","year":"2018","journal-title":"Proc NeurIPS"}],"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\/10097113.pdf?arnumber=10097113","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:07:31Z","timestamp":1700507251000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10097113\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10097113","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}