{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T22:31:49Z","timestamp":1768775509783,"version":"3.49.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[[2019,12]]},"DOI":"10.1109\/icmla.2019.00127","type":"proceedings-article","created":{"date-parts":[[2020,2,18]],"date-time":"2020-02-18T09:58:47Z","timestamp":1582019927000},"page":"706-711","source":"Crossref","is-referenced-by-count":20,"title":["Low-Bit Quantization and Quantization-Aware Training for Small-Footprint Keyword Spotting"],"prefix":"10.1109","author":[{"given":"Yuriy","family":"Mishchenko","sequence":"first","affiliation":[{"name":"Amazon.com"}]},{"given":"Yusuf","family":"Goren","sequence":"additional","affiliation":[{"name":"Amazon.com"}]},{"given":"Ming","family":"Sun","sequence":"additional","affiliation":[{"name":"Amazon.com"}]},{"given":"Chris","family":"Beauchene","sequence":"additional","affiliation":[{"name":"Amazon.com"}]},{"given":"Spyros","family":"Matsoukas","sequence":"additional","affiliation":[{"name":"Amazon.com"}]},{"given":"Oleg","family":"Rybakov","sequence":"additional","affiliation":[{"name":"Amazon.com"}]},{"given":"Shiv Naga Prasad","family":"Vitaladevuni","sequence":"additional","affiliation":[{"name":"Amazon.com"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Dorefanet: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"zhou","year":"2016","journal-title":"arXiv preprint arXiv 1606 06160"},{"key":"ref11","article-title":"Trained ternary quantization","author":"zhu","year":"2016","journal-title":"arXiv preprint arXiv 1612 01064"},{"key":"ref12","article-title":"Loss-aware binarization of deep networks","author":"hou","year":"2016","journal-title":"arXiv preprint arXiv 1611 01600"},{"key":"ref13","article-title":"Extremely low bit neural network: Squeeze the last bit out with ADMM","author":"leng","year":"2017","journal-title":"arXiv preprint arXiv 1707 06892"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-128"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"1063","DOI":"10.21437\/Interspeech.2014-275","article-title":"Boundary contraction training for acoustic models based on discrete deep neural networks","author":"takeda","year":"2014","journal-title":"Proc INTERSPEECH 2014"},{"key":"ref16","article-title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","author":"krishnamoorthi","year":"2018","journal-title":"arXiv preprint arXiv 1806 08342"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-480"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638949"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855087"},{"key":"ref28","article-title":"A cascade architecture for keyword spotting on mobile devices","author":"gruenstein","year":"2018","journal-title":"arXiv preprint arXiv 1712 03603"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846306"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1485"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1562"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"1478","DOI":"10.21437\/Interspeech.2015-352","article-title":"Convolutional neural networks for small-footprint keyword spotting","author":"sainath","year":"2015","journal-title":"Proceedings of Interspeech 2015"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"1473","DOI":"10.21437\/Interspeech.2015-351","article-title":"Compressing deep neural networks using a rank-constrained topology","author":"nakkiran","year":"2015","journal-title":"Proceedings of Interspeech 2015"},{"key":"ref8","article-title":"Retraining-based iterative weight quantization for deep neural networks","author":"lee","year":"2018","journal-title":"arXiv preprint arXiv 1805 11233"},{"key":"ref7","article-title":"Training and inference with integers in deep neural networks","author":"wu","year":"2018","journal-title":"arXiv preprint arXiv 1802 10363"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2015.121"},{"key":"ref9","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":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854370"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1393"},{"key":"ref22","article-title":"8-bit inference with TensorRT","author":"migacz","year":"2017"},{"key":"ref21","first-page":"1737","article-title":"Deep learning with limited numerical precision","author":"gupta","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref24","article-title":"Compression of acoustic event detection models with low-rank matrix factorization and quantization training","author":"shi","year":"2018","journal-title":"NeurIPS 2018 workshop on Compact Deep Neural Networks with industrial applications"},{"key":"ref23","article-title":"Model compression via distillation and quantization","author":"polino","year":"2018","journal-title":"arXiv preprint arxiv 1802 05807"},{"key":"ref26","article-title":"Scalable distributed DNN training using commodity GPU cloud computing","author":"strom","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1747"}],"event":{"name":"2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)","location":"Boca Raton, FL, USA","start":{"date-parts":[[2019,12,16]]},"end":{"date-parts":[[2019,12,19]]}},"container-title":["2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8974348\/8998966\/08999090.pdf?arnumber=8999090","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,15]],"date-time":"2022-10-15T21:15:25Z","timestamp":1665868525000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8999090\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icmla.2019.00127","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}