{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:51:04Z","timestamp":1753602664055,"version":"3.28.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446041","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"876-880","source":"Crossref","is-referenced-by-count":2,"title":["MOS-FAD: Improving Fake Audio Detection Via Automatic Mean Opinion Score Prediction"],"prefix":"10.1109","author":[{"given":"Wangjin","family":"Zhou","sequence":"first","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengdong","family":"Yang","sequence":"additional","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenhui","family":"Chu","sequence":"additional","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Li","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology (NICT),Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raj","family":"Dabre","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology (NICT),Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Zhao","sequence":"additional","affiliation":[{"name":"Kuaishou Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kawahara","family":"Tatsuya","sequence":"additional","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"article-title":"Fast-speech: Fast, robust and controllable text to speech","volume-title":"Proc. NeurIPS","author":"Ren","key":"ref2"},{"article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. ICLR","author":"Ren","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2968"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-930"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-794"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2249"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1111"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.01.001"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-472"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-847"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747768"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1794"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3174"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-360"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"DARTS: differentiable architecture search","volume-title":"Proc. ICLR","author":"Liu","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1187"},{"key":"ref22","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","volume":"33","author":"Baevski"},{"article-title":"Representation learning with contrastive predictive coding","volume-title":"Proc. NeurIPS","author":"Oord","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00860"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-970"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383533"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747222"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9746395"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10262"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. ICML","author":"Baevski","key":"ref35"},{"key":"ref36","article-title":"Lightgbm: A highly efficient gradient boosting d\u2019e\u2019c\u2019i\u2019s\u2019i\u2019o\u2019n tree","volume-title":"Proc. NeurIPS","volume":"30","author":"Ke"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446041.pdf?arnumber=10446041","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:01:39Z","timestamp":1722574899000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446041\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446041","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}