{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:32:56Z","timestamp":1780587176791,"version":"3.54.1"},"reference-count":50,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8461870","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"5934-5938","source":"Crossref","is-referenced-by-count":275,"title":["The Microsoft 2017 Conversational Speech Recognition System"],"prefix":"10.1109","author":[{"given":"W.","family":"Xiong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"L.","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"F.","family":"Alleva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J.","family":"Droppo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"X.","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"A.","family":"Stolcke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.879814"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953159"},{"key":"ref33","article-title":"Convolutional, long short-term memory, fully connected deep neural networks","author":"sainath","year":"2015","journal-title":"Proc IEEE ICASSP"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-251"},{"key":"ref30","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume":"37","author":"ioffe","year":"2015","journal-title":"Machine Learning Research"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1460"},{"key":"ref36","first-page":"55","article-title":"Speaker adaptation of neural network acoustic models using i-vectors","author":"saon","year":"2013","journal-title":"Proc IEEE Workshop Speech Recognition Understanding"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref34","article-title":"The SRI March 2000 Hub-5 conversational speech transcription system","author":"stolcke","year":"2000","journal-title":"Proc NIST Speech Transcription Workshop College Park MD"},{"key":"ref28","article-title":"Highway networks","author":"srivastava","year":"2015","journal-title":"CoRR vol abs\/1505 00387"},{"key":"ref27","author":"he","year":"2015","journal-title":"Deep residual learning for image recognition"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472646"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.59.2229"},{"key":"ref1","article-title":"Insights into spoken language gleaned from phonetic transcription of the Switchboard corpus","author":"greenberg","year":"1996","journal-title":"Proc ICSLP"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-33486-6_6"},{"key":"ref22","article-title":"Achieving human parity in conversational speech recognition","author":"xiong","year":"2016","journal-title":"Microsoft Research Tech Rep MSR-TR"},{"key":"ref21","first-page":"746","article-title":"Linguistic regularities in continuous space word representations","volume":"13","author":"mikolov","year":"2013","journal-title":"HLT-NAACL"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"132","DOI":"10.21437\/Interspeech.2017-405","article-title":"English conversational telephone speech recognition by humans and machines","author":"saon","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"137","DOI":"10.21437\/Interspeech.2017-1544","article-title":"Comparing human and machine errors in conversational speech transcription","author":"stolcke","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref26","first-page":"2915","article-title":"Transcription methods for consistency, volume and efficiency","author":"glenn","year":"2010","journal-title":"Proc Int Conf on Lang Resources and Evaluation"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"1323","DOI":"10.21437\/Interspeech.2017-1695","article-title":"Deep learning-based telephony speech recognition in the wild","author":"han","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2001.1034659"},{"key":"ref10","first-page":"338","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref11","first-page":"1468","article-title":"Fast and accurate recurrent neural network acoustic models for speech recognition","author":"sak","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-595"},{"key":"ref12","first-page":"3140","article-title":"The IBM 2015 English conversational telephone speech recognition system","author":"saon","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472620"},{"key":"ref14","first-page":"3259","article-title":"Very deep convolutional neural networks for LVCSR","author":"bi","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2602884"},{"key":"ref16","first-page":"1045","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"Proc Inter-speech"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"194","DOI":"10.21437\/Interspeech.2012-65","article-title":"LSTM neural networks for language modeling","author":"sundermeyer","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref18","first-page":"2","article-title":"Improving English conversational telephone speech recognition","author":"medennikov","year":"2016","journal-title":"Proc Inter-speech"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref5","article-title":"Convolutional networks for images, speech, and time series","volume":"3361","author":"lecun","year":"1995","journal-title":"The Handbook of Brain Theory and Neural Networks"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/0885-2308(91)90010-N"},{"key":"ref49","first-page":"2002","article-title":"SRILM-an extensible language modeling toolkit","author":"stolcke","year":"2002","journal-title":"Proc INTERSPEECH"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"437","DOI":"10.21437\/Interspeech.2011-169","article-title":"Conversational speech transcription using context-dependent deep neural networks","author":"seide","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref46","year":"0","journal-title":"The Microsoft Cognition Toolkit (CNTK)"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/1073483.1073486"},{"key":"ref48","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015"},{"key":"ref47","first-page":"1058","article-title":"1-bit stochastic gradient descent and its application to data-parallel distributed training of speech DNNs","author":"seide","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref42","first-page":"5450","article-title":"Self-stabilized deep neural network","author":"ghahremani","year":"2016","journal-title":"Proc IEEE ICASSP"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2400218"},{"key":"ref44","article-title":"Conversational session-level language modeling with LSTMs","author":"xiong","year":"2017","journal-title":"Submitted to IEEE ICASSP-2018"},{"key":"ref43","author":"press","year":"2016","journal-title":"Using the output embedding to improve language models"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Calgary, AB","start":{"date-parts":[[2018,4,15]]},"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\/08461870.pdf?arnumber=8461870","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,5]],"date-time":"2023-09-05T09:07:25Z","timestamp":1693904845000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461870\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8461870","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}