{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T23:07:41Z","timestamp":1729638461492,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/slt.2018.8639551","type":"proceedings-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T23:36:34Z","timestamp":1550187394000},"page":"219-226","source":"Crossref","is-referenced-by-count":7,"title":["LSTM Language Model Adaptation with Images and Titles for Multimedia Automatic Speech Recognition"],"prefix":"10.1109","author":[{"given":"Yasufumi","family":"Moriya","sequence":"first","affiliation":[]},{"given":"Gareth J. F.","family":"Jones","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proceedings of Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref11","first-page":"487","article-title":"Learning deep features for scene recognition using places database","author":"zhou","year":"2014","journal-title":"Proceedings of Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref12","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref13","first-page":"248","article-title":"ImageNet: A large-scale hierarchical image database","author":"jia","year":"2009","journal-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"year":"2009","author":"bird","journal-title":"Natural Language Processing With Python","key":"ref14"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1162\/tacl_a_00051"},{"key":"ref16","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proceedings of Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref17","article-title":"Towards Universal Paraphrastic Sentence Embeddings","author":"wieting","year":"2016","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref18","article-title":"A simple but tough to beat baseline for sentence embeddings","author":"arora","year":"2017","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/CVPR.2015.7298935"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/ICASSP.2016.7472829"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ASRU.2015.7404863"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/CVPR.2017.345"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ASRU.2013.6707758"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/ICASSP.2018.8462439"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/ICASSP.2017.7953112"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.21437\/Interspeech.2010-343","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"Proceedings of Interspeech"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/SLT.2016.7846320"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/TASLP.2015.2438543"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1162\/neco.1997.9.8.1735"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1561\/1500000020"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref22","first-page":"2","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"peddinti","year":"2015","journal-title":"Proceedings of Interspeech"},{"key":"ref21","first-page":"1","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc IEEE Workshop Automatic Speech Recognition and Understanding (ASRU)"},{"key":"ref24","article-title":"SRILM-an extensible language modeling toolkit","author":"stolcke","year":"2002","journal-title":"Proc Int Conf Spoken Language Processing (ICSLP)"},{"key":"ref23","first-page":"310","article-title":"An empirical study of smoothing techniques for language modeling","author":"chen","year":"1995","journal-title":"Computer Speech and Language"},{"key":"ref26","first-page":"157","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume":"5","author":"xu","year":"2015","journal-title":"IEEE Transactions on Neural Networks"},{"key":"ref25","first-page":"1","article-title":"Automatic differentiation in PyTorch","author":"paszke","year":"2017","journal-title":"Proceedings of Advances in Neural Information Processing Systems (NIPS)"}],"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\/08639551.pdf?arnumber=8639551","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T17:14:36Z","timestamp":1694625276000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8639551\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/slt.2018.8639551","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}