{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:40:50Z","timestamp":1760132450242,"version":"3.28.0"},"reference-count":37,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,3]]},"DOI":"10.1109\/icassp.2017.7953112","type":"proceedings-article","created":{"date-parts":[[2017,6,20]],"date-time":"2017-06-20T17:35:36Z","timestamp":1497980136000},"page":"5020-5024","source":"Crossref","is-referenced-by-count":20,"title":["Visual features for context-aware speech recognition"],"prefix":"10.1109","author":[{"given":"Abhinav","family":"Gupta","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yajie","family":"Miao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leonardo","family":"Neves","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian","family":"Metze","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Lasagne: First release","author":"dieleman","year":"2015","journal-title":"Zenodo"},{"key":"ref32","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"Journal of Machine Learning Res"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424228"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"article-title":"Translating videos to natural language using deep recurrent neural networks","year":"2014","author":"venugopalan","key":"ref36"},{"key":"ref35","article-title":"Multimodal neural language models","author":"kiros","year":"2014","journal-title":"Proc ICML"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3210"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853591"},{"key":"ref11","article-title":"Towards speaker adaptive training of deep neural network acoustic models","author":"miao","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2457612"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"ref14","first-page":"2440","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"peddinti","year":"2015","journal-title":"Proceedings of Interspeech ISCA"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472692"},{"key":"ref16","article-title":"Distance-aware DNNs for robust speech recognition","author":"miao","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/6046.865479"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/79.911195"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319179"},{"key":"ref28","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc ASRU"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707758"},{"key":"ref27","first-page":"487","article-title":"Learning deep features for scene recognition using places database","author":"zhou","year":"2014","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163899"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2014.6890234"},{"article-title":"Kaldi+pdnn: building dnn-based asr systems with kaldi and pdnn","year":"2014","author":"miao","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-412"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"journal-title":"Neural speech recognizer Acoustic-to-word lstm model for large vocabulary speech recognition","year":"2016","author":"soltau","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854823"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.940793"},{"key":"ref22","article-title":"Deep residual learning for image recognition","volume":"abs 1512 3385","author":"he","year":"2015","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/35.41402"},{"key":"ref24","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078568"},{"key":"ref26","first-page":"275","article-title":"Deep sparse rectifier neural networks","volume":"15","author":"glorot","year":"2011","journal-title":"AISTATS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"}],"event":{"name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2017,3,5]]},"location":"New Orleans, LA","end":{"date-parts":[[2017,3,9]]}},"container-title":["2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7943262\/7951776\/07953112.pdf?arnumber=7953112","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,8,29]],"date-time":"2017-08-29T14:48:53Z","timestamp":1504018133000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7953112\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp.2017.7953112","relation":{},"subject":[],"published":{"date-parts":[[2017,3]]}}}