{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T23:31:42Z","timestamp":1729639902342,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,7]]},"DOI":"10.1109\/ccoms.2017.8075276","type":"proceedings-article","created":{"date-parts":[[2017,10,25]],"date-time":"2017-10-25T19:47:55Z","timestamp":1508960875000},"page":"101-105","source":"Crossref","is-referenced-by-count":7,"title":["An improved residual LSTM architecture for acoustic modeling"],"prefix":"10.1109","author":[{"given":"Lu","family":"Huang","sequence":"first","affiliation":[]},{"given":"Ji","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Jiasong","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Very deep convolutional networks for end-to-end speech recognition","year":"2016","author":"zhang","key":"ref10"},{"journal-title":"Deep Learning for Speaker Recognition","year":"0","author":"selvaraj","key":"ref11"},{"journal-title":"Identification of nonlinear systems using dynamic neural networks","year":"2016","author":"ogunmolu","key":"ref12"},{"key":"ref13","article-title":"Timit acoustic-phonetic continuous speech corpus","author":"garofolo","year":"1993","journal-title":"Linguistic Data Consortium Philadelphia"},{"journal-title":"THCHS-30 A Free Chinese Speech Corpus","year":"2015","author":"wang","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref16","article-title":"Switchboard-1 Release 2 LDC97S62","author":"godfrey","year":"1993","journal-title":"Web Download Philadelphia Linguistic Data Consortium"},{"journal-title":"Supervised Sequence Labelling with Recurrent Neural Networks","year":"2008","author":"kawakami","key":"ref17"},{"key":"ref18","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472084"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"ref4","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":"ref27","first-page":"69","article-title":"The Fisher Corpus: A Resource for the Next Generations of Speech-to-Text","volume":"4","author":"cieri","year":"2004","journal-title":"International Conference on Language Resources and Evaluation (LREC)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"journal-title":"Residual LSTM Design of a Deep Recurrent Architecture for Distant Speech Recognition","year":"2017","author":"kim","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"journal-title":"Achieving human parity in conversational speech recognition","year":"2016","author":"xiong","key":"ref8"},{"journal-title":"English conversational telephone speech recognition by humans and machines","year":"2017","author":"saon","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"journal-title":"The microsoft 2016 conversational speech recognition system","year":"2016","author":"xiong","key":"ref9"},{"key":"ref1","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":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref22","article-title":"Parallel training of Deep Neural Networks with Natural Gradient and Parameter Averaging","author":"povey","year":"2015","journal-title":"International Conference on Learning Representations ICLR 2015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5724-z"},{"key":"ref24","first-page":"285","article-title":"Phone recognition on the TIMIT database","volume":"1","author":"lopes","year":"2011","journal-title":"Speech Technologies"},{"key":"ref23","article-title":"Audio augmentation for speech recognition","author":"ko","year":"2015","journal-title":"Proc INTERSPEECH"},{"journal-title":"Web Download","article-title":"2000 HUB5 English Evaluation Speech LDC2002S09","year":"2002","key":"ref26"},{"journal-title":"THCHS-30 CHALLENGE","year":"0","key":"ref25"}],"event":{"name":"2017 2nd International Conference on Computer and Communication Systems (ICCCS)","start":{"date-parts":[[2017,7,11]]},"location":"Krakow, Poland","end":{"date-parts":[[2017,7,14]]}},"container-title":["2017 2nd International Conference on Computer and Communication Systems (ICCCS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8055814\/8075168\/08075276.pdf?arnumber=8075276","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,5]],"date-time":"2022-08-05T11:42:45Z","timestamp":1659699765000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8075276\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/ccoms.2017.8075276","relation":{},"subject":[],"published":{"date-parts":[[2017,7]]}}}