{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T22:49:32Z","timestamp":1785365372266,"version":"3.55.0"},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,3]]},"DOI":"10.1109\/icassp.2017.7952190","type":"proceedings-article","created":{"date-parts":[[2017,6,20]],"date-time":"2017-06-20T21:35:36Z","timestamp":1497994536000},"page":"421-425","source":"Crossref","is-referenced-by-count":248,"title":["Very deep convolutional neural networks for raw waveforms"],"prefix":"10.1109","author":[{"given":"Wei","family":"Dai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chia","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuhui","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juncheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samarjit","family":"Das","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Convolutional neural networks for acoustic modeling of raw time signal in lvcsr","author":"golik","year":"2015","journal-title":"Sixteenth Annual Conference of the InternationalSpeech Communication Association"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2015.7324337"},{"key":"ref12","author":"ioffe","year":"2015","journal-title":"Batch Normalization Accelerating Deep Network Training by Reducing Internal Covariate Shift"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref14","article-title":"Dropout: A simple way to prevent neural networks from overfitting","author":"srivastava","year":"0","journal-title":"Journal of Machine Learning Research 2014"},{"key":"ref15","author":"simonyan","year":"2014","journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638312"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472620"},{"key":"ref4","article-title":"Learning the speech frontend with raw waveform cldnns","author":"sainath","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178847"},{"key":"ref6","author":"he","year":"2015","journal-title":"Deep residual learning for image recognition"},{"key":"ref5","first-page":"1106","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.220"},{"key":"ref2","author":"hannun","year":"2014","journal-title":"Deep speech Scaling up end-to-end speech recognition"},{"key":"ref1","article-title":"CP-JKU submissions for DCASE-2016: a hybrid approach using binaural i-vectors and deep convolutional neural networks","author":"eghbal-zadeh","year":"2016","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"890","DOI":"10.21437\/Interspeech.2014-223","article-title":"Acoustic modeling with deep neural networks using raw time signal for lvcsr","author":"t\u00fcske","year":"2014","journal-title":"InterSpeech"},{"key":"ref20","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref22","author":"abadi","year":"2016","journal-title":"Tensorflow Large-scale machine learning on heterogeneous distributed systems"},{"key":"ref21","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"9","author":"glorot","year":"2010","journal-title":"AISTATS"}],"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\/07952190.pdf?arnumber=7952190","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T20:59:52Z","timestamp":1750366792000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7952190\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp.2017.7952190","relation":{},"subject":[],"published":{"date-parts":[[2017,3]]}}}