{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:48:42Z","timestamp":1776887322248,"version":"3.51.2"},"reference-count":22,"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.2019.8683705","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"5716-5720","source":"Crossref","is-referenced-by-count":27,"title":["A Highly Adaptive Acoustic Model for Accurate Multi-dialect Speech Recognition"],"prefix":"10.1109","author":[{"given":"Sanghyun","family":"Yoo","sequence":"first","affiliation":[{"name":"Samsung Advanced Institute of Technology, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Inchul","family":"Song","sequence":"additional","affiliation":[{"name":"Samsung Advanced Institute of Technology, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshua","family":"Bengio","sequence":"additional","affiliation":[{"name":"Mila, Université de Montréal, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_48"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.23915\/distill.00011","article-title":"Feature-wise transformations","author":"dumoulin","year":"2018","journal-title":"Distillation"},{"key":"ref12","article-title":"Multi-accent deep neural network acoustic model with accent-specific top layer using the kld-regularized model adaptation","author":"huang","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref13","article-title":"A learned representation for artistic style","author":"dumoulin","year":"2015","journal-title":"Proc ICLR"},{"key":"ref14","article-title":"Layer normalization","volume":"abs 1607 6450","author":"ba","year":"2016","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472159"},{"key":"ref16","article-title":"Deep speech 2: End-to-end speech recognition in English and Mandarin","author":"amodei","year":"2016","journal-title":"Proc ICML"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639211"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref19","year":"0","journal-title":"ASR corpus"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-556"},{"key":"ref3","article-title":"Improving deep neural networks based multi-accent mandarin speech recognition using i-vectors and accent-specific top layer","author":"chen","year":"2015","journal-title":"Proc INTERSPEECH ISCA"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1864"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462557"},{"key":"ref8","article-title":"FiLM: Visual reasoning with a general conditioning layer","author":"perez","year":"2017","journal-title":"Proc AAAI IEEE"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461886"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846328"},{"key":"ref9","article-title":"Modulating early visual processing by language","author":"de vries","year":"2017","journal-title":"Proc NIPS"},{"key":"ref20","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref22","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref21","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, UK","start":{"date-parts":[[2019,5,12]]},"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\/08683705.pdf?arnumber=8683705","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:19:06Z","timestamp":1755800346000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683705\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683705","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}