{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T08:28:16Z","timestamp":1729672096732,"version":"3.28.0"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[[2019,12]]},"DOI":"10.1109\/asru46091.2019.9003755","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T02:01:33Z","timestamp":1582250493000},"page":"980-987","source":"Crossref","is-referenced-by-count":2,"title":["Unsupervised Adaptation of Acoustic Models for ASR Using Utterance-Level Embeddings from Squeeze and Excitation Networks"],"prefix":"10.1109","author":[{"given":"Hardik B.","family":"Sailor","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Salil","family":"Deena","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Md Asif","family":"Jalal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rasa","family":"Lileikyte","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Hain","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"DARPA TIMIT Acoustic Phonetic Continuous Speech Corpus CDROM","year":"1993","author":"garofolo","key":"ref39"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1158"},{"key":"ref33","first-page":"5984","article-title":"Do-main and speaker adaptation for Cortana speech recognition","author":"zhao","year":"2018","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"122","DOI":"10.21437\/Interspeech.2017-460","article-title":"Embedding-based speaker adaptive training of deep neural networks","author":"cui","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-556"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472692"},{"key":"ref37","first-page":"6000","article-title":"Attention is all you need","author":"ashish","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682386"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2762739"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2584700"},{"key":"ref40","first-page":"94","article-title":"Aurora working group: DSR front end LVCSR evaluation au\/384\/02","volume":"40","author":"parihar","year":"2002","journal-title":"Tech Rep"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1244"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2511922"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2798821"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178785"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2825432"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462629"},{"key":"ref17","first-page":"109","article-title":"Improved feature processing for deep neural networks","author":"shakti","year":"2013","journal-title":"InterSpeech"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2457612"},{"key":"ref28","article-title":"Invariant representations for noisy speech recognition","author":"serdyuk","year":"2016","journal-title":"NIPS workshop on end-to-end speech recognition"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660239"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-879"},{"key":"ref3","first-page":"526","article-title":"Comparison of discriminative input and output transformations for speaker adaptation in the hybrid NN\/HMM systems","author":"li","year":"2010","journal-title":"INTER-SPEECH'10"},{"key":"ref6","first-page":"5711","article-title":"BL-HUC: Bayesian learning of hidden unit contributions for deep neural network speaker adaptation","author":"xie","year":"2019","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref29","article-title":"Latent dirichlet allocation based organisation of broadcast media archives for deep neural network adaptation","author":"oscar","year":"2015","journal-title":"Proc IEEE Workshop Automatic Speech Recognition and Understanding (ASRU)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2560534"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639201"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639212"},{"key":"ref2","article-title":"Speaker-adaptation for hybrid HMM-ANN continuous speech recognition system","author":"paulo da silva neto","year":"1995","journal-title":"EU-ROSPEECH"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1897"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1247"},{"key":"ref20","first-page":"2180","article-title":"Adaptation of deep neural network acoustic models using factorised i-vectors","author":"penny","year":"2014","journal-title":"Proc INTERSPEECH 2014"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2602884"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"1713","DOI":"10.1109\/TASLP.2014.2346313","article-title":"Fast adaptation of deep neural network based on discriminant codes for speech recognition","volume":"22","author":"xue","year":"2014","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref47","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11671","article-title":"FiLM: Visual reasoning with a general conditioning layer","author":"perez","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853591"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683713"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-405"},{"key":"ref41","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc IEEE Workshop Automatic Speech Recognition and Understanding (ASRU)"},{"key":"ref23","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","author":"ganin","year":"2015","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref44","article-title":"Quaternion recurrent neural networks","author":"parcollet","year":"2019","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461932"},{"key":"ref43","first-page":"2564","article-title":"Understanding the representation and computation of multilayer perceptrons: A case study in speech recognition","author":"nagamine","year":"2017","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461648"}],"event":{"name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2019,12,14]]},"location":"SG, Singapore","end":{"date-parts":[[2019,12,18]]}},"container-title":["2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8985378\/9003727\/09003755.pdf?arnumber=9003755","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,27]],"date-time":"2023-09-27T04:49:41Z","timestamp":1695790181000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9003755\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/asru46091.2019.9003755","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}