{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T17:11:12Z","timestamp":1769015472355,"version":"3.49.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413565","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"2750-2754","source":"Crossref","is-referenced-by-count":2,"title":["Train Your Classifier First: Cascade Neural Networks Training from Upper Layers to Lower Layers"],"prefix":"10.1109","author":[{"given":"Shucong","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Cong-Thanh","family":"Do","sequence":"additional","affiliation":[]},{"given":"Rama","family":"Doddipatla","sequence":"additional","affiliation":[]},{"given":"Erfan","family":"Loweimi","sequence":"additional","affiliation":[]},{"given":"Peter","family":"Bell","sequence":"additional","affiliation":[]},{"given":"Steve","family":"Renals","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2702"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1438"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682224"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2025"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1973"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref12","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref13","article-title":"Regularizing and optimizing LSTM language models","author":"merity","year":"2018","journal-title":"ICLRE"},{"key":"ref14","article-title":"Forward thinking: Building and training neural networks one layer at a time","author":"hettinger","year":"2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545535"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2018.00608"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2805098"},{"key":"ref18","article-title":"Greedy layerwise learning can scale to ImageNet","author":"belilovsky","year":"2019","journal-title":"ICML"},{"key":"ref19","article-title":"Training neural networks with local error signals","author":"n\u00f8kland","year":"2019","journal-title":"ICML"},{"key":"ref28","article-title":"First-pass large vocabulary continuous speech recognition using bi-directional recurrent DNNs","author":"hannun","year":"2014"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424230"},{"key":"ref27","article-title":"Automatic differentiation in PyTorch","author":"paszke","year":"2017","journal-title":"NeurIPS Autodiff Workshop"},{"key":"ref3","article-title":"Deep learning of representations for unsupervised and transfer learning","author":"bengio","year":"2012","journal-title":"ICML Workshop"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639655"},{"key":"ref29","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"ICML"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639084"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref2","article-title":"How transferable are features in deep neural networks?","author":"yosinski","year":"2014","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref1","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"NeurIPS"},{"key":"ref20","article-title":"Learning noise invariant features through transfer learning for robust end-to-end speech recognition","author":"zhang","year":"2020","journal-title":"ICASSP"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00116-6"},{"key":"ref21","article-title":"Dropout: a simple way to prevent neural networks from overfitting","author":"srivastava","year":"2014","journal-title":"JMLR"},{"key":"ref24","article-title":"ADADELTA: an adaptive learning rate method","author":"zeiler","year":"2012"},{"key":"ref23","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","author":"duchi","year":"2011","journal-title":"JMLR"},{"key":"ref26","article-title":"Incorporating Nesterov momentum into Adam","author":"dozat","year":"2016","journal-title":"ICLR Workshop 2016"},{"key":"ref25","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413565.pdf?arnumber=9413565","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:40:57Z","timestamp":1652182857000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413565\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413565","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}