{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T05:21:03Z","timestamp":1782451263445,"version":"3.54.5"},"reference-count":54,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,5]]},"DOI":"10.1109\/icassp.2013.6639344","type":"proceedings-article","created":{"date-parts":[[2013,10,29]],"date-time":"2013-10-29T23:19:46Z","timestamp":1383088786000},"page":"8599-8603","source":"Crossref","is-referenced-by-count":773,"title":["New types of deep neural network learning for speech recognition and related applications: an overview"],"prefix":"10.1109","author":[{"given":"Li","family":"Deng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Geoffrey","family":"Hinton","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian","family":"Kingsbury","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"35","article-title":"Building high-level features using large scale unsupervised learning","author":"le","year":"2012","journal-title":"ICML"},{"key":"36","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"33","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(90)90044-L"},{"key":"34","article-title":"The neural autoregressive distributed estimator","author":"larochelle","year":"2011","journal-title":"ICML"},{"key":"39","article-title":"Deep learning via Hessian-free optimization","author":"martens","year":"2010","journal-title":"ICML"},{"key":"37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960588"},{"key":"38","author":"markoff","year":"2012","journal-title":"Scientists See Promise in Deep-Learning Programs"},{"key":"43","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109382"},{"key":"42","article-title":"Deep belief networks for phone recognition","author":"mohamed","year":"2009","journal-title":"Proc NIPS Workshop Deep Learn Speech Recogn Relat Applicat"},{"key":"41","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-343","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"InterSpeech"},{"key":"40","article-title":"Learning recurrent neural networks with hessian-free optimization","author":"martens","year":"2011","journal-title":"ICML"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639348"},{"key":"23","author":"hinton","year":"2012","journal-title":"Improving Neural Networks by Preventing Coadaptation of Feature Detectors"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"27","author":"hinton","year":"2012","journal-title":"Improving Neural Networks by Preventing Coadaptation of Feature Detectors"},{"key":"28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639140"},{"key":"29","article-title":"Crosslanguage knowledge transfer using multilingual deep neural networks with shared hidden layers","author":"huang","year":"2013","journal-title":"ICASSP"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639349"},{"key":"2","article-title":"Exploring convolutional neural network structures and optimization for speech recognition","author":"abdel-hamid","year":"2013","journal-title":"InterSpeech"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288864"},{"key":"30","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-10","article-title":"Application of pretrained deep neural networks to large vocabulary speech recognition","author":"jaitly","year":"2012","journal-title":"InterSpeech"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"6","author":"bourlard","year":"1993","journal-title":"Connectionist Speech Recognition A Hybrid Approach"},{"key":"32","article-title":"ImageNet classification with deep convolutional neural Networks","author":"krizhevsky","year":"2012","journal-title":"NIPS"},{"key":"5","article-title":"Large scale online learning","author":"bottou","year":"2004","journal-title":"NIPS"},{"key":"31","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-3","article-title":"Scalable minimum Bayes risk training of deep neural network acoustic models using distributed Hessian-free optimization","author":"kingsbury","year":"2012","journal-title":"InterSpeech"},{"key":"4","first-page":"281","article-title":"Random search for hyperparameter optimization","volume":"3","author":"bergstra","year":"2012","journal-title":"J Machine Learning Research"},{"key":"9","article-title":"Improving DNNs for LVCSR using rectified linear units and dropout","author":"dahl","year":"2013","journal-title":"ICASSP"},{"key":"8","article-title":"Large vocabulary continuous speech recognition with context-dependent DBNHMMs","author":"dahl","year":"2011","journal-title":"ICASSP"},{"key":"19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424224"},{"key":"17","article-title":"Deep learning for speech recognition and related applications","author":"deng","year":"2009","journal-title":"NIPS Workshop"},{"key":"18","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-487","article-title":"Binary coding of speech spectrograms using a deep auto-encoder","author":"deng","year":"2010","journal-title":"InterSpeech"},{"key":"15","article-title":"Use of differential cepstra as acoustic features in hidden trajectory modeling for phonetic recognition","author":"deng","year":"2007","journal-title":"ICASSP"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288333"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638952"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878265"},{"key":"11","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"NIPS"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639345"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"20","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","author":"duchi","year":"2011","journal-title":"J Machine Learning Research"},{"key":"49","doi-asserted-by":"crossref","first-page":"437","DOI":"10.21437\/Interspeech.2011-169","article-title":"Conversational speech transcription using context-dependent deep neural networks","author":"seide","year":"2011","journal-title":"Interspeech 2011"},{"key":"48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639347"},{"key":"45","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"ICML"},{"key":"44","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2116010"},{"key":"47","doi-asserted-by":"publisher","DOI":"10.1109\/72.279192"},{"key":"46","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163900"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"51","author":"sutskever","year":"2013","journal-title":"Training Recurrent Neural Networks"},{"key":"52","author":"yu","year":"2011","journal-title":"Discriminative Pretraining of Deep Neural Networks"},{"key":"53","article-title":"Roles of pretraining and finetuning in context-dependent DNN-HMMs for real-world speech recognition","author":"yu","year":"2010","journal-title":"NIPS Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638312"},{"key":"50","article-title":"Practical Bayesian optimization of machine learning algorithms","author":"snoek","year":"2012","journal-title":"NIPS"}],"event":{"name":"ICASSP 2013 - 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Vancouver, BC, Canada","start":{"date-parts":[[2013,5,26]]},"end":{"date-parts":[[2013,5,31]]}},"container-title":["2013 IEEE International Conference on Acoustics, Speech and Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6619549\/6637585\/06639344.pdf?arnumber=6639344","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T22:48:00Z","timestamp":1646952480000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6639344\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,5]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/icassp.2013.6639344","relation":{},"subject":[],"published":{"date-parts":[[2013,5]]}}}