{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T10:08:27Z","timestamp":1770890907144,"version":"3.50.1"},"reference-count":33,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,3]]},"DOI":"10.1109\/icassp.2017.7953077","type":"proceedings-article","created":{"date-parts":[[2017,6,20]],"date-time":"2017-06-20T21:35:36Z","timestamp":1497994536000},"page":"4845-4849","source":"Crossref","is-referenced-by-count":220,"title":["Very deep convolutional networks for end-to-end speech recognition"],"prefix":"10.1109","author":[{"given":"Yu","family":"Zhang","sequence":"first","affiliation":[]},{"given":"William","family":"Chan","sequence":"additional","affiliation":[]},{"given":"Navdeep","family":"Jaitly","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","article-title":"Towards End-to-End Speech Recognition with Recurrent Neural Networks","author":"graves","year":"2014","journal-title":"ICML"},{"key":"ref32","article-title":"TensorFlow: large-scale machine learning on heterogeneous systems","author":"abadi","year":"2015","journal-title":"software available from tensorflow org"},{"key":"ref31","article-title":"Adam: A Method for Stochastic Optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"key":"ref30","article-title":"Practical Variational Inference for Neural Networks","author":"graves","year":"2011","journal-title":"NIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639347"},{"key":"ref11","article-title":"Deep Convolutional Neural Networks for Acoustic Modeling in Low Resource Languages","author":"chan","year":"2016","journal-title":"ICA SSP"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707749"},{"key":"ref14","article-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","author":"simonyan","year":"2015","journal-title":"ICLRE"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472620"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1033"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2602884"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref19","article-title":"Network in network","author":"lin","year":"2013","journal-title":"ICLRE"},{"key":"ref28","article-title":"Grid long short-term memory","author":"kalchbrenner","year":"2016","journal-title":"ICLRE"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref27","article-title":"Training very deep networks","author":"srivastava","year":"2015","journal-title":"NIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-334"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472780"},{"key":"ref5","article-title":"Task Loss Estimation for Sequence Prediction","author":"bahdanau","year":"2016","journal-title":"ICLR Workshop"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref7","article-title":"Sequence Transduction with Recurrent Neural Networks","author":"graves","year":"2012","journal-title":"ICML Representation Learning Worksop"},{"key":"ref2","article-title":"Attention-Based Models for Speech Recognition","author":"chorowski","year":"2015","journal-title":"NIPS"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2013-744","article-title":"Exploring Convolutional Neural Network Structures and Optimization Techniques for Speech Recognition","author":"abdel-hamid","year":"2013","journal-title":"InterSpeech"},{"key":"ref1","article-title":"Neural Machine Translation by Jointly Learning to Align and Translate","author":"bahdanau","year":"2015","journal-title":"ICLRE"},{"key":"ref20","article-title":"Hierarchical Recurrent Neural Networks for Long-Term Dependencies","author":"hihi","year":"1996","journal-title":"NIPS"},{"key":"ref22","article-title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin","author":"amodei","year":"2016","journal-title":"ICML"},{"key":"ref21","article-title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","author":"ioffe","year":"2015","journal-title":"ICML"},{"key":"ref24","article-title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","author":"shi","year":"2015","journal-title":"NIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707742"}],"event":{"name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"New Orleans, LA","start":{"date-parts":[[2017,3,5]]},"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\/07953077.pdf?arnumber=7953077","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T20:58:08Z","timestamp":1750366688000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7953077\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp.2017.7953077","relation":{},"subject":[],"published":{"date-parts":[[2017,3]]}}}