{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T18:54:32Z","timestamp":1767207272670,"version":"3.48.0"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100000646","name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","doi-asserted-by":"publisher","award":["11K17945"],"award-info":[{"award-number":["11K17945"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3648378","type":"journal-article","created":{"date-parts":[[2025,12,25]],"date-time":"2025-12-25T18:27:16Z","timestamp":1766687236000},"page":"216748-216758","source":"Crossref","is-referenced-by-count":0,"title":["Excitement-Inducing Commentary Text-to-Speech System for Fighting Game Video Scenes"],"prefix":"10.1109","volume":"13","author":[{"given":"Kota","family":"Iura","sequence":"first","affiliation":[{"name":"The University of Tokyo, Hongo, Bunkyo-ku, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7967-2613","authenticated-orcid":false,"given":"Yuki","family":"Saito","sequence":"additional","affiliation":[{"name":"The University of Tokyo, Hongo, Bunkyo-ku, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0520-7847","authenticated-orcid":false,"given":"Shinnosuke","family":"Takamichi","sequence":"additional","affiliation":[{"name":"The University of Tokyo, Hongo, Bunkyo-ku, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Graham","family":"Neubig","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katsuhito","family":"Sudoh","sequence":"additional","affiliation":[{"name":"Nara Women’s University, Kitauoya Nishimachi, Nara, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0876-5617","authenticated-orcid":false,"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[{"name":"The University of Tokyo, Hongo, Bunkyo-ku, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroya","family":"Takamura","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology, Koto-ku, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuya","family":"Ishigaki","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology, Koto-ku, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2465958.2465971"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1051\/shsconf\/20219204002"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1111\/j.1460-2466.1982.tb00482.x"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3415174"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00513"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-srw.28"},{"key":"ref7","first-page":"9","article-title":"Audio commentary system for real-time racing game play","volume-title":"Proc. INLG","author":"Ishigaki"},{"key":"ref8","first-page":"6571","article-title":"SMASH corpus: A spontaneous speech corpus recording third-person audio commentaries on gameplay","volume-title":"Proc. LREC","author":"Saito"},{"key":"ref9","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proc. ICML","author":"Wang"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053732"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3341105.3374063"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.99"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017096"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00381"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-75538-8_2"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2015.7317930"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/BMSB47279.2019.8971879"},{"key":"ref18","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL","author":"Devlin"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.09.001"},{"key":"ref21","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. ICML","author":"Kim"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10294"},{"article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ren","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1779"},{"article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2000.903548"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45103-x_50"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1250\/ast.41.761"},{"article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov","key":"ref31"},{"key":"ref32","first-page":"120","article-title":"The OpenCV library","volume":"25","author":"Bradski","year":"2000","journal-title":"Dr. Dobb\u2019s J. Softw. Tools"},{"key":"ref33","first-page":"4480","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume-title":"Proc. NeurIPS","author":"Ye"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11316119.pdf?arnumber=11316119","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T18:45:24Z","timestamp":1767206724000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11316119\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3648378","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}