{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T04:30:33Z","timestamp":1746246633896,"version":"3.28.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053483","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7939-7943","source":"Crossref","is-referenced-by-count":5,"title":["Low-bit Quantization of Recurrent Neural Network Language Models Using Alternating Direction Methods of Multipliers"],"prefix":"10.1109","author":[{"given":"Junhao","family":"Xu","sequence":"first","affiliation":[]},{"given":"Xie","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Shoukang","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Jianwei","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Xunying","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"Improving the speed of neural networks on cpus","year":"2011","author":"vanhoucke","key":"ref39"},{"key":"ref38","first-page":"6869","article-title":"Quantized neural networks: Training neural networks with low precision weights and activations","volume":"18","author":"hubara","year":"2017","journal-title":"The Journal of Machine Learning Research"},{"key":"ref33","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"han","year":"2016","journal-title":"ICLRE"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461550"},{"key":"ref31","first-page":"197","article-title":"Structured output layer neural network language models for speech recognition","volume":"21","author":"le","year":"2012","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref30","article-title":"Improved neural network based language modelling and adaptation","author":"park","year":"2010","journal-title":"Eleventh Annual Conference of the International Speech Communication Association"},{"key":"ref37","article-title":"Trained ternary quantization","author":"zhu","year":"2016","journal-title":"NIPS Workshop on Efficient Methods for Deep Neural Networks"},{"article-title":"An extragradient method for finding saddle points and for other problems, konom. i mat","year":"1976","author":"korpelevi","key":"ref36"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1139"},{"key":"ref34","first-page":"2177","article-title":"Neural word embedding as implicit matrix factorization","author":"levy","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref10","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref40","article-title":"Training binary multilayer neural networks for image classification using expectation backpropagation","author":"cheng","year":"2015","journal-title":"arXiv preprint arXiv 1503"},{"key":"ref11","first-page":"2074","article-title":"Learning structured sparsity in deep neural networks","author":"wen","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Training deep neural networks with low precision multiplications","author":"courbariaux","year":"2015","journal-title":"a workshop contribution at ICLR"},{"key":"ref13","first-page":"3123","article-title":"Binaryconnect: Training deep neural networks with binary weights during propagations","author":"courbariaux","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1","author":"courbariaux","year":"2016","journal-title":"Proceedings of the Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1192"},{"key":"ref16","article-title":"Compressing deep convolutional networks using vector quantization","author":"gong","year":"2014","journal-title":"arXiv preprint arXiv 1412 6115"},{"key":"ref17","first-page":"2285","article-title":"Compressing neural networks with the hashing trick","author":"chen","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref18","first-page":"963","article-title":"Expectation backpropagation: Parameter-free training of multilayer neural networks with continuous or discrete weights","author":"soudry","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"article-title":"Automatic differentiation in pytorch","year":"2017","author":"paszke","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638949"},{"article-title":"An extragradient method for finding saddle points and for other problems","year":"1976","author":"korpelevi?","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1589"},{"key":"ref6","article-title":"Speeding-up convolutional neural networks using fine-tuned cp-decomposition","author":"lebedev","year":"2015","journal-title":"ICLRE"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2007.4430100"},{"key":"ref5","article-title":"Speeding up convolutional neural networks with low rank expansions","author":"jaderberg","year":"2014","journal-title":"British Machine Vision Conference"},{"key":"ref8","first-page":"3088","article-title":"Structured transforms for small-footprint deep learning","author":"sindhwani","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Convolutional neural networks with low-rank regularization","author":"tai","year":"2016","journal-title":"ICLRE"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1190"},{"key":"ref9","first-page":"806","article-title":"Sparse convolutional neural networks","author":"liu","year":"2015","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref1","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2014","journal-title":"Deep Learning and Representation Learning Workshop NIPS"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11713","article-title":"Extremely low bit neural network: Squeeze the last bit out with admm","author":"leng","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref22","first-page":"1137","article-title":"A neural probabilistic language model","volume":"3","author":"bengio","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref21","article-title":"Alternating multi-bit quantization for recurrent neural networks","author":"xu","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref24","article-title":"Lstm neural networks for language modeling","author":"sundermeyer","year":"2012","journal-title":"Thirteenth Annual Conference of the International Speech Communication Association"},{"key":"ref23","first-page":"473","article-title":"Lstm can solve hard long time lag problems","author":"hochreiter","year":"1997","journal-title":"Advances in neural information processing systems"},{"key":"ref26","article-title":"Ternary weight networks","author":"li","year":"2016","journal-title":"arXiv preprint arXiv 1605 04711"},{"key":"ref25","first-page":"525","article-title":"Xnornet: Imagenet classification using binary convolutional neural networks","author":"rastegari","year":"2016","journal-title":"European Conference on Computer Vision"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053483.pdf?arnumber=9053483","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T19:27:58Z","timestamp":1696015678000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053483\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053483","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}