{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T21:04:28Z","timestamp":1762808668806,"version":"3.41.2"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2018,4,1]],"date-time":"2018-04-01T00:00:00Z","timestamp":1522540800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2018,4,1]],"date-time":"2018-04-01T00:00:00Z","timestamp":1522540800000},"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":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8461553","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"5984-5988","source":"Crossref","is-referenced-by-count":12,"title":["Domain and Speaker Adaptation for Cortana Speech Recognition"],"prefix":"10.1109","author":[{"given":"Yong","family":"Zhao","sequence":"first","affiliation":[{"name":"Microsoft Corporation, One Microsoft Way, Redmond, WA 98052, USA"}]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, One Microsoft Way, Redmond, WA 98052, USA"}]},{"given":"Shixiong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, One Microsoft Way, Redmond, WA 98052, USA"}]},{"given":"Liping","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, One Microsoft Way, Redmond, WA 98052, USA"}]},{"given":"Yifan","family":"Gong","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, One Microsoft Way, Redmond, WA 98052, USA"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1570","article-title":"Robust speech recognition via anchor word representations","author":"king","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1249"},{"key":"ref33","article-title":"Fast speaker adaptation of hybrid NN\/HMM model for speech recognition based on discriminative learning of speaker code","author":"abdel-hamid","year":"2013","journal-title":"Proc ICASSP"},{"key":"ref32","article-title":"Factorized adaptation for deep neural network","author":"li","year":"2014","journal-title":"Proc ICASSP"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-5779-3_11"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref37","doi-asserted-by":"crossref","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"},{"key":"ref36","article-title":"Low-rank plus diagonal adaptation for deep neural networks","author":"zhao","year":"2016","journal-title":"Proc ICASSP"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2601146"},{"key":"ref34","article-title":"Towards speaker adaptive training of deep neural network acoustic models","author":"miao","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref10","article-title":"Speaker adaptation of context dependent deep neural networks","author":"liao","year":"2013","journal-title":"Proc ICASSP"},{"key":"ref40","article-title":"Extended low-rank plus diagonal adaptation for deep and recurrent neural networks","author":"zhao","year":"2017","journal-title":"Proc ICASSP"},{"key":"ref11","article-title":"KL-divergence regularized deep neural network adaptation for improved large vocabulary speech recognition","author":"yu","year":"2013","journal-title":"Proc ICASSP"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-519","article-title":"Large-scale domain adaptation via teacher-student learning","author":"li","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref13","article-title":"SVD-based universal DNN modeling for multiple scenarios","author":"liu","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref14","article-title":"Domain adaptation of DNN acoustic models using knowledge distillation","author":"asami","year":"2017","journal-title":"Proc ICASSP"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.1995-411","article-title":"Speaker-adaptation for hybrid HMM-ANN continuous speech recognition system","author":"neto","year":"1995","journal-title":"Proc EUROSPEECH"},{"key":"ref16","article-title":"Comparison of discriminative input and output transformations for speaker adaptation in the hybrid NN\/HMM systems","author":"li","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref17","article-title":"Feature engineering in context-dependent deep neural networks for conversational speech transcription","author":"seide","year":"2011","journal-title":"Proc IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.11.005"},{"key":"ref19","article-title":"Adaptation of context-dependent deep neural networks for automatic speech recognition","author":"yao","year":"2012","journal-title":"Proc IEEE Workshop on Spoken Language Technology"},{"key":"ref28","article-title":"I-vector-based speaker adaptation of deep neural networks for french broadcast audio transcription","author":"gupta","year":"2014","journal-title":"Proc ICASSP"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2017.7510508"},{"key":"ref27","article-title":"Speaker adaptation of neural network acoustic models using i-vectors","author":"saon","year":"2013","journal-title":"Proc IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref3","article-title":"Recent advances in deep learning for speech research at Microsoft","author":"deng","year":"2013","journal-title":"Proc ICASSP"},{"key":"ref6","article-title":"Speech recognition with deep recurrent neural networks","author":"graves","year":"2013","journal-title":"Proc ICASSP"},{"key":"ref29","article-title":"Improving DNN speaker independence with i-vector inputs","author":"senior","year":"2014","journal-title":"Proc ICASSP"},{"key":"ref5","article-title":"Making deep belief networks effective for large vocabulary continuous speech recognition","author":"sainath","year":"2011","journal-title":"Proc IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref8","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref7","article-title":"Hybrid speech recognition with deep bidirectional LSTM","author":"graves","year":"2013","journal-title":"Proc IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref2","article-title":"Application of pre-trained deep neural networks to large vocabulary speech recognition","author":"jaitly","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref9","article-title":"Simplifying long short-term memory acoustic models for fast training and decoding","author":"miao","year":"2016","journal-title":"Proc ICASSP"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref20","article-title":"On speaker adaptation of long short-term memory recurrent neural networks","author":"miao","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref22","article-title":"Restructuring of deep neural network acoustic models with singular value decomposition","author":"xue","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref21","article-title":"Learning hidden unit contributions for unsupervised speaker adaptation of neural network acoustic models","author":"swietojanski","year":"2014","journal-title":"Proc IEEE Spoken Language Technology Workshop"},{"key":"ref42","article-title":"An introduction to computational networks and the computational network toolkit","author":"agarwal","year":"2014","journal-title":"Microsoft Technical Report MSR-TR-2014–112"},{"key":"ref24","article-title":"Investigating online low-footprint speaker adaptation using generalized linear regression and click-through data","author":"zhao","year":"2015","journal-title":"Proc ICASSP"},{"key":"ref41","article-title":"I-vector dependent feature space transformations for adaptive speech recognition","author":"li","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref23","article-title":"Singular value decomposition based low-footprint speaker adaptation and personalization for deep neural network","author":"xue","year":"2014","journal-title":"Proc ICASSP"},{"key":"ref44","article-title":"End-to-end text-dependent speaker verification","author":"heigold","year":"2016","journal-title":"Proc ICASSP"},{"key":"ref26","article-title":"Learning representations by back-propagating errors","author":"rumelhart","year":"1988","journal-title":"Cognitive Modeling"},{"key":"ref43","article-title":"Deep neural networks for small footprint text-dependent speaker verification","author":"variani","year":"2014","journal-title":"Proc ICASSP"},{"key":"ref25","article-title":"Maxi-mum a posteriori adaptation of network parameters in deep models","author":"huang","year":"2015","journal-title":"Proc INTERSPEECH"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2018,4,15]]},"location":"Calgary, AB, Canada","end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08461553.pdf?arnumber=8461553","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T18:10:09Z","timestamp":1751998209000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461553\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8461553","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}