{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:15:43Z","timestamp":1761581743907,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/icip.2018.8451096","type":"proceedings-article","created":{"date-parts":[[2018,9,7]],"date-time":"2018-09-07T17:59:22Z","timestamp":1536343162000},"page":"4138-4142","source":"Crossref","is-referenced-by-count":21,"title":["Audio-Visual Keyword Spotting Based on Multidimensional Convolutional Neural Network"],"prefix":"10.1109","author":[{"given":"Runwei","family":"Ding","sequence":"first","affiliation":[]},{"given":"Cheng","family":"Pang","sequence":"additional","affiliation":[]},{"given":"Hong","family":"Liu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"1606","article-title":"Convolutional recurrent neural networks for small-footprint keyword spotting","author":"sercan","year":"2017","journal-title":"InterSpeech"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1109\/TCYB.2013.2250954","article-title":"Robust audio-visual speech recognition under noisy audio-video conditions","volume":"44","author":"darryl","year":"2014","journal-title":"IEEE Transactions on Cybernetics"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/TASLP.2015.2409785"},{"key":"ref13","first-page":"4561","article-title":"Audio-visual speaker identification with multi-view distance metric learning","author":"haomain","year":"2010","journal-title":"IEEE International Conference on Image Processing"},{"key":"ref14","first-page":"2589","article-title":"Audio-visual emotion recognition using boltzmann zippers","author":"kun","year":"2012","journal-title":"IEEE International Conference on Image Processing"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/ICASSP.2004.1326662"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1109\/TMM.2016.2520091","article-title":"A novel lip descriptor for audio-visual keyword spotting based on adaptive decision fusion","volume":"18","author":"pingping","year":"2016","journal-title":"IEEE Transactions on Multimedia"},{"key":"ref17","first-page":"1867","article-title":"One millisecond face alignment with an ensemble of regression trees","author":"vahid","year":"2014","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref18","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"nitish","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","article-title":"Assessment for automatic speech recognition: Ii. noisex-92: A database and an experiment to study the effect of additive noise on speech recognition systems","volume":"12","author":"andrew","year":"1993","journal-title":"Speech Communication"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"1618","DOI":"10.1109\/TASLP.2017.2703650","article-title":"Bin-aural sound localization based on reverberation weighting and generalized parametric mapping","volume":"25","author":"cheng","year":"2017","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref3","first-page":"210","article-title":"Score normalization and system combination for improved keyword spotting","author":"damianos","year":"2013","journal-title":"IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"1870","DOI":"10.1109\/29.103088","article-title":"Automatic recognition of keywords in unconstrained speech using hidden markov models","volume":"38","author":"jay","year":"1990","journal-title":"IEEE Transactions on Acoustics Speech and Signal Processing"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/MSP.2012.2197156","article-title":"Large-vocabulary continuous speech recognition systems: A look at some recent advances","volume":"29","author":"george","year":"2012","journal-title":"IEEE Signal Processing Magazine"},{"key":"ref8","first-page":"4087","article-title":"Small-footprint keyword spotting using deep neural networks","author":"guoguo","year":"2014","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1007\/s10772-013-9217-1","article-title":"Recent developments in spoken term detection: a survey","volume":"17","author":"anupam","year":"2014","journal-title":"International Journal of Speech Technology"},{"key":"ref2","first-page":"1","article-title":"Word topic models for spoken document retrieval and transcription","volume":"8","author":"berlin","year":"2009","journal-title":"ACM Transactions on Asian Language Information Processing"},{"key":"ref1","first-page":"3949","article-title":"Robust discriminative keyword spotting for emotionally colored spontaneous speech using bidirectional lstm networks","author":"martin","year":"2009","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref9","first-page":"1478","article-title":"Convolutional neural networks for small-footprint keyword spotting","author":"tara","year":"2015","journal-title":"InterSpeech"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"633","DOI":"10.21437\/Interspeech.2005-69","article-title":"Comparison of keyword spotting approaches for informal continuous speech","author":"szoke","year":"2005","journal-title":"InterSpeech"}],"event":{"name":"2018 25th IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2018,10,7]]},"location":"Athens","end":{"date-parts":[[2018,10,10]]}},"container-title":["2018 25th IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8436606\/8451009\/08451096.pdf?arnumber=8451096","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T07:02:25Z","timestamp":1643180545000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8451096\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icip.2018.8451096","relation":{},"subject":[],"published":{"date-parts":[[2018,10]]}}}