{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T02:40:39Z","timestamp":1755830439972,"version":"3.44.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683724","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"8643-8647","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal Speaker Adaptation of Acoustic Model and Language Model for Asr Using Speaker Face Embedding"],"prefix":"10.1109","author":[{"given":"Yasufumi","family":"Moriya","sequence":"first","affiliation":[{"name":"ADAPT Centre, Dublin City University, Ireland"}]},{"given":"Gareth J. F.","family":"Jones","sequence":"additional","affiliation":[{"name":"ADAPT Centre, Dublin City University, Ireland"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Lstm language model adaptation with images and titles for multimedia automatic speech recognition","author":"moriya","year":"0","journal-title":"Spoken Language Technology Workshop (SLT)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078568"},{"key":"ref14","first-page":"3007","article-title":"Speaker adaptation of DNN-based ASR with i-vectors: Does it actually adapt models to speakers?","author":"rouvier","year":"2014","journal-title":"InterSpeech"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.02.003"},{"key":"ref16","first-page":"157","article-title":"Improving speaker diarization of tv series using talking-face detection and clustering","author":"herve","year":"2016","journal-title":"ACM Multimedia (ACMMM)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1334"},{"key":"ref18","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"king","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404863"},{"key":"ref27","first-page":"1","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Automatic Speech Recognition and Understanding (ASRU)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0408949102"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953112"},{"key":"ref5","first-page":"121","article-title":"Grounded language modeling for automatic speech recognition of sports video","author":"fleischman","year":"2008","journal-title":"ACL-08 HLT"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2003.817150"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/science.7777863"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462439"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref20","first-page":"2","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"peddinti","year":"2015","journal-title":"InterSpeech"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.21437\/Interspeech.2010-343","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"InterSpeech"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref23","article-title":"How2: a large-scale dataset for multimodal language understanding","author":"sanabria","year":"2018","journal-title":"Proceedings of the Workshop on Visually Grounded Interaction and Language (ViGIL) NeurIPS"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.21437\/ICSLP.2002-303","article-title":"SRILM-an extensible language modeling toolkit","author":"stolcke","year":"2002","journal-title":"International Conference on Spoken Language Processing (ICSLP)"},{"key":"ref25","first-page":"310","article-title":"An empirical study of smoothing techniques for language modeling","author":"chen","year":"1995","journal-title":"Computer Speech and Language"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, UK","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683724.pdf?arnumber=8683724","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:18:55Z","timestamp":1755800335000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683724\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683724","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}