{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T07:30:08Z","timestamp":1725607808855},"reference-count":37,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/slt.2018.8639637","type":"proceedings-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T18:36:34Z","timestamp":1550169394000},"page":"456-462","source":"Crossref","is-referenced-by-count":3,"title":["Exploring Layer Trajectory LSTM with Depth Processing Units and Attention"],"prefix":"10.1109","author":[{"given":"Jinyu","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changliang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Deep residual learning for image recognition","author":"he","year":"2015","journal-title":"arXiv preprint arXiv 1512 03385"},{"key":"ref32","first-page":"2365","article-title":"Restructuring of deep neural network acoustic models with singular value decomposition","author":"xue","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461558"},{"key":"ref30","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv preprint arXiv 1409 0473"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462209"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855088"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707763"},{"key":"ref34","article-title":"Maxout networks","author":"goodfellow","year":"2013","journal-title":"arXiv preprint arXiv 1302 4389"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178826"},{"key":"ref11","first-page":"1101","article-title":"On speaker adaptation of long short-term memory recurrent neural networks","author":"miao","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472084"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref14","article-title":"LSTM time and frequency recurrence for automatic speech recognition","author":"li","year":"2015","journal-title":"ASRU"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472617"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-84"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1164","article-title":"Reducing the computational complexity of two-dimensional LSTMs","author":"li","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2017.7510508"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472780"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-548"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-10","article-title":"Application of pretrained deep neural networks to large vocabulary speech recognition","author":"jaitly","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref27","article-title":"Scalable minimum bayes risk training of deep neural network acoustic models using distributed hessian-free optimization","author":"kingsbury","year":"2012","journal-title":"Thirteenth Annual Conference of the International Speech Communication Association"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639345"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638951"},{"key":"ref8","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":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163900"},{"key":"ref1","article-title":"Roles of pre-training and fine-tuning in context-dependent dbn-hmms for real-world speech recognition","author":"yu","year":"2010","journal-title":"NIPS 2010 Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"ref9","article-title":"Sequence discriminative distributed training of long short-term memory recurrent neural networks","author":"sak","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1109\/SLT.2016.7846305","article-title":"A prioritized grid long short-term memory RNN for speech recognition","author":"hsu","year":"2016","journal-title":"Spoken Language Technology Workshop (SLT) IEEE"},{"key":"ref22","article-title":"Residual LSTM: Design of a deep recurrent architecture for distant speech recognition","author":"kim","year":"2017","journal-title":"arXiv preprint arXiv 1701 03360"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-677"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1485"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-429","article-title":"Highway-LSTM and recurrent highway networks for speech recognition","author":"pundak","year":"2017","journal-title":"Proc of Interspeech"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1109\/ASRU.2017.8268957","article-title":"Automatic speech recognition of Arabic multi-genre broadcast media","author":"najafian","year":"2017","journal-title":"Automatic Speech Recognition and Understanding (ASRU) 2017 IEEE Workshop on"},{"key":"ref25","article-title":"Grid long short-term memory","author":"kalchbrenner","year":"2015","journal-title":"arXiv preprint arXiv 1507 01526"}],"event":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2018,12,18]]},"location":"Athens, Greece","end":{"date-parts":[[2018,12,21]]}},"container-title":["2018 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8632666\/8639030\/08639637.pdf?arnumber=8639637","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T02:57:12Z","timestamp":1643252232000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8639637\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/slt.2018.8639637","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}