{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T05:27:51Z","timestamp":1738128471622,"version":"3.33.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2024,12,3]]},"DOI":"10.1109\/apsipaasc63619.2025.10848599","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:37:05Z","timestamp":1738003025000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Real-Time Noise Estimation for Lombard-Effect Speech Synthesis in Human\u2013Avatar Dialogue Systems"],"prefix":"10.1109","author":[{"given":"Yuto","family":"Ishikawa","sequence":"first","affiliation":[{"name":"The University of Tokyo,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Osamu","family":"Take","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomohiko","family":"Nakamura","sequence":"additional","affiliation":[{"name":"The National Institute of Advanced Industrial Science and Technology (AIST),Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Norihiro","family":"Takamune","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Saito","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinnosuke","family":"Takamichi","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05204-1_21"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-9443-0_6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2304637"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3166054.3166058"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3554727"},{"article-title":"A survey on neural speech synthesis","year":"2021","author":"Tan","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10627448"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2011517"},{"key":"ref10","first-page":"101","article-title":"Le signe de l\u2019elevation de la voix","volume":"37","author":"Lombard","year":"1911","journal-title":"Annales Maladies de L\u2019Oreille et du Larynx"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1044\/1092-4388(2001\/038)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2577880"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3003165"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(00)00345-3"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1155\/S1110865703305074"},{"key":"ref16","first-page":"1941","article-title":"Blind source separation for moving speech signals using blockwise ICA and residual crosstalk subtraction","volume":"E87-A","author":"Mukai","year":"2004","journal-title":"IEICE Trans. Fundamentals"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1155\/ASP\/2006\/34970"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1250\/ast.41.761"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1554"},{"article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. ICLR","author":"Ren","key":"ref21"},{"key":"ref22","first-page":"17 022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurlIPS","author":"Kong"}],"event":{"name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2024,12,3]]},"location":"Macau, Macao","end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10848542\/10848533\/10848599.pdf?arnumber=10848599","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:22:52Z","timestamp":1738045372000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10848599\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc63619.2025.10848599","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}