{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:29:05Z","timestamp":1775230145765,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1109\/icassp.2016.7472780","type":"proceedings-article","created":{"date-parts":[[2016,6,24]],"date-time":"2016-06-24T01:58:30Z","timestamp":1466733510000},"page":"5755-5759","source":"Crossref","is-referenced-by-count":144,"title":["Highway long short-term memory RNNS for distant speech recognition"],"prefix":"10.1109","author":[{"given":"Yu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoguo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaisheng","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanjeev","family":"Khudanpur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Glass","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205285"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2163395"},{"key":"ref12","article-title":"Making the most from multiple microphones in meeting recognition","author":"stolcke","year":"2011","journal-title":"ICASSP"},{"key":"ref13","article-title":"Training deep bidirectional lstm acoustic model for lvcsr by a context-sensitive-chunk bptt approach","author":"chen","year":"2015","journal-title":"InterSpeech"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"1120","DOI":"10.1109\/LSP.2014.2325781","article-title":"Convolutional neural networks for distant speech recognition","volume":"21","author":"swietojanski","year":"2014","journal-title":"IEEE Singal Processing Letters"},{"key":"ref15","article-title":"An introduction to computational networks and the computational network toolkit","author":"yu","year":"2014","journal-title":"Microsoft Technical Report"},{"key":"ref16","article-title":"Highway networks","author":"srivastava","year":"2015"},{"key":"ref17","article-title":"Depth-gated lstm","author":"yao","year":"2015"},{"key":"ref18","article-title":"Grid long short-term memory","author":"kalchbrenner","year":"2015"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639100"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"1120","DOI":"10.1109\/LSP.2014.2325781","article-title":"Convolutional neural networks for distant speech recognition","volume":"21","author":"swietojanski","year":"2014","journal-title":"Signal Processing Letters IEEE"},{"key":"ref8","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"ref2","first-page":"437","article-title":"Conversational speech transcription using context -dependent deep neural networks","author":"seide","year":"2011","journal-title":"Proc Annual Conference of International Speech Communication Association (INTERSPEECH)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707744"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","article-title":"Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition","volume":"20","author":"dahl","year":"2012","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854672"},{"key":"ref22","article-title":"Multiple dimension levenshtein edit distance calculations for evaluating asr systems during simultaneous speech","author":"fiscus","year":"2006","journal-title":"LREC"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-007-9040-x"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163899"},{"key":"ref23","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"ASRU"},{"key":"ref26","article-title":"Improving neural networks by preventing co-adaptation of feature detectors","author":"hinton","year":"2012"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1990.2.4.490"}],"event":{"name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Shanghai","start":{"date-parts":[[2016,3,20]]},"end":{"date-parts":[[2016,3,25]]}},"container-title":["2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7465907\/7471614\/07472780.pdf?arnumber=7472780","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,6,25]],"date-time":"2020-06-25T20:43:57Z","timestamp":1593117837000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7472780\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp.2016.7472780","relation":{},"subject":[],"published":{"date-parts":[[2016,3]]}}}