{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:04:30Z","timestamp":1730297070624,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/slt.2018.8639675","type":"proceedings-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T23:36:34Z","timestamp":1550187394000},"page":"77-83","source":"Crossref","is-referenced-by-count":2,"title":["Improving Very Deep Time-Delay Neural Network With Vertical-Attention For Effectively Training CTC-Based ASR Systems"],"prefix":"10.1109","author":[{"given":"Sheng","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xugang","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryoichi","family":"Takashima","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuya","family":"Kawahara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hisashi","family":"Kawai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","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":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-71"},{"key":"ref31","first-page":"15","article-title":"Development of the SprinTra WFST speech decoder","author":"dixon","year":"2012","journal-title":"NICT Research Journal"},{"key":"ref30","first-page":"1023","article-title":"Maximum-a-Posterioribased decoding for End-to-End acoustic models","volume":"25","author":"kanda","year":"2017","journal-title":"IEEE Trans on ASLP"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472805"},{"key":"ref34","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953070"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"ref12","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"peddinti","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref13","article-title":"Feedforward sequential memory networks: A new structure to learn long-term dependency","author":"zhang","year":"2015","journal-title":"arXiv preprint arXiv 1512 00327"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-185"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1475"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1475"},{"key":"ref18","first-page":"550","article-title":"Residual networks behave like ensembles of relatively shallow networks","author":"veit","year":"2016","journal-title":"Proc NIPS"},{"key":"ref19","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"NIPS"},{"key":"ref28","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Proc NIPS"},{"key":"ref4","article-title":"Very deep convolutional neural networks for LVCSR","author":"bi","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref27","article-title":"Benchmark test for speech recognition using the corpus of spontaneous japanese","author":"kawahara","year":"2003","journal-title":"Proc ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953077"},{"key":"ref29","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proceedings of IEEE ASRU"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2602884"},{"key":"ref8","article-title":"Deep-FSMN for large vocaburary continuous speech recognition","author":"zhang","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-251"},{"key":"ref2","article-title":"Towards End-to-End speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc ICML"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462523"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref22","article-title":"Feed-forward networks with attention can solve some long-term memory problems","author":"raffel","year":"2016","journal-title":"arXiv preprint arXiv 1512 00327"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1296","article-title":"Advances in joint CTC-Attention based End-to-End speech recognition with a deep CNN Encoder and RNN-LM","author":"hori","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462497"},{"key":"ref23","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref26","article-title":"Kaldi recipe for Japanese spontaneous speech recognition and its evaluation","author":"moriya","year":"2015","journal-title":"Autumn Meeting of ASJ"},{"key":"ref25","article-title":"Corpus of spontaneous japanese: Its design and evaluation","author":"maekawa","year":"2003","journal-title":"Proc ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition"}],"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\/08639675.pdf?arnumber=8639675","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T05:53:20Z","timestamp":1643262800000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8639675\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/slt.2018.8639675","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}