{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T19:40:01Z","timestamp":1749843601630,"version":"3.41.0"},"reference-count":34,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,8]]},"DOI":"10.1109\/eusipco.2016.7760373","type":"proceedings-article","created":{"date-parts":[[2016,12,19]],"date-time":"2016-12-19T21:08:29Z","timestamp":1482181709000},"page":"873-877","source":"Crossref","is-referenced-by-count":3,"title":["Unsupervised learning of temporal receptive fields using convolutional RBM for ASR task"],"prefix":"10.1109","author":[{"given":"Hardik B.","family":"Sailor","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hemant A.","family":"Patil","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref32","first-page":"873","article-title":"Sparse deep belief net model for visual area V2","author":"lee","year":"2007","journal-title":"Proceedings of the 21st Annual Conference on Neural Information Processing Systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref30","first-page":"27403","article-title":"DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. NIST speech disc 1–1.1","volume":"93","author":"garofolo","year":"1993","journal-title":"NASA STI\/Recon Technical Report N"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/29.46546"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nn831"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947700"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472808"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1155\/S1110865703303051"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553453"},{"key":"ref15","first-page":"1737","article-title":"Using an autoencoder with deformable templates to discover features for automated speech recognition","author":"jaitly","year":"2013","journal-title":"14th Annual Conference of the International Speech Communication Association Interspeech 2013"},{"key":"ref16","first-page":"2346","article-title":"Phone classification by a hierarchy of invariant representation layers","author":"zhang","year":"2014","journal-title":"INTERSPEECH 2014 15th Annual Conference of the International Speech Communication Association"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178840"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2607341"},{"key":"ref19","first-page":"1096","article-title":"Unsupervised feature learning for audio classification using convolutional deep belief networks","author":"lee","year":"2009","journal-title":"23rd Annual Conference on Neural Information Processing Systems"},{"key":"ref28","volume":"355","author":"lee","year":"2012","journal-title":"Automatic Speech and Speaker Recognition Advanced Topics"},{"key":"ref4","first-page":"1","article-title":"Learning the speech front-end with raw waveform CLDNNs","author":"sainath","year":"2015","journal-title":"InterSpeech"},{"key":"ref27","first-page":"2321","article-title":"The topographic unsupervised learning of natural sounds in the auditory cortex","author":"terashima","year":"2012","journal-title":"Proceedings of 26th Annual Conference on Neural Information Processing Systems 2012"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1121\/1.399423"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178781"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2011.03.001"},{"key":"ref5","first-page":"26","article-title":"Convolutional neural networks for acoustic modeling of raw time signal in LVCSR","author":"golik","year":"2015","journal-title":"InterSpeech"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref7","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref9","first-page":"1631","article-title":"Speech feature extraction using independent component analysis","volume":"3","author":"lee","year":"2000","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref20","first-page":"194","article-title":"Information processing in dynamical systems: Foundations of harmony theory","volume":"1","author":"smolensky","year":"1986","journal-title":"Parallel Distributed Processing Explorations in the Microstructure of Cognition"},{"key":"ref22","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"27th International Conference on Machine Learning (ICML)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref24","first-page":"1971","article-title":"Unsupervised learning models of primary cortical receptive fields and receptive field plasticity","author":"saxe","year":"2011","journal-title":"Annual Conference on Neural Information Processing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638312"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"ref25","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"2011","journal-title":"International Conference on Artificial Intelligence and Statistics (AISTATS)"}],"event":{"name":"2016 24th European Signal Processing Conference (EUSIPCO)","start":{"date-parts":[[2016,8,29]]},"location":"Budapest, Hungary","end":{"date-parts":[[2016,9,2]]}},"container-title":["2016 24th European Signal Processing Conference (EUSIPCO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7740646\/7760191\/07760373.pdf?arnumber=7760373","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T19:05:27Z","timestamp":1749841527000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7760373\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,8]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/eusipco.2016.7760373","relation":{},"subject":[],"published":{"date-parts":[[2016,8]]}}}