{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T20:48:59Z","timestamp":1761598139547,"version":"3.28.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.23919\/eusipco.2019.8902524","type":"proceedings-article","created":{"date-parts":[[2019,11,25]],"date-time":"2019-11-25T18:39:38Z","timestamp":1574707178000},"page":"1-5","source":"Crossref","is-referenced-by-count":10,"title":["CNN-based Multichannel End-to-End Speech Recognition for Everyday Home Environments"],"prefix":"10.23919","author":[{"given":"Nelson","family":"Yalta","sequence":"first","affiliation":[{"name":"Waseda University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takaaki","family":"Hori","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuhiro","family":"Nakadai","sequence":"additional","affiliation":[{"name":"Honda Research Institute,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tetsuya","family":"Ogata","sequence":"additional","affiliation":[{"name":"Waseda University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref32","article-title":"ADADELTA: an adaptive learning rate method","volume":"abs 1212 5701","author":"zeiler","year":"2012","journal-title":"CoRR"},{"key":"ref31","article-title":"Chainer: a next-generation open source framework for deep learning","author":"tokui","year":"2015","journal-title":"Proceedings of Workshop on Machine Learning Systems (LearningSys) in NIPS"},{"key":"ref30","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472641"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-11"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1768"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-3"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-2"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-1"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-9"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2672401"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","article-title":"End-to-end continuous speech recognition using attention-based recurrent NN: First results","author":"chorowski","year":"2014","journal-title":"NIPS Workshop on Deep Learning"},{"key":"ref27","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"NIPS"},{"key":"ref3","article-title":"Linear prediction-based dereverberation with advanced speech enhancement and recognition technologies for the reverb challenge","author":"delcroix","year":"2014","journal-title":"Reverb Challenge Workshop"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref29","article-title":"Skip connections as effective symmetry-breaking","volume":"abs 1701 9175","author":"orhan","year":"2017","journal-title":"CoRR"},{"key":"ref5","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"2016","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref8","article-title":"Acoustic modeling for Google home","author":"li","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854663"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref20","first-page":"2632","article-title":"Multichannel end-to-end speech recognition","author":"ochiai","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953077"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268948"},{"key":"ref23","first-page":"1945","article-title":"Batch renormalization: Towards reducing minibatch dependence in batch-normalized models","author":"ioffe","year":"2017","journal-title":"NIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366923"}],"event":{"name":"2019 27th European Signal Processing Conference (EUSIPCO)","start":{"date-parts":[[2019,9,2]]},"location":"A Coruna, Spain","end":{"date-parts":[[2019,9,6]]}},"container-title":["2019 27th European Signal Processing Conference (EUSIPCO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8893974\/8902336\/08902524.pdf?arnumber=8902524","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,24]],"date-time":"2023-01-24T19:14:10Z","timestamp":1674587650000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8902524\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9]]},"references-count":34,"URL":"https:\/\/doi.org\/10.23919\/eusipco.2019.8902524","relation":{},"subject":[],"published":{"date-parts":[[2019,9]]}}}