{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:56:51Z","timestamp":1730199411094,"version":"3.28.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389686","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T13:38:40Z","timestamp":1705671520000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["The Role of Feature Correlation on Quantized Neural Networks"],"prefix":"10.1109","author":[{"given":"David","family":"Qiu","sequence":"first","affiliation":[{"name":"Google, LLC"}]},{"given":"Shaojin","family":"Ding","sequence":"additional","affiliation":[{"name":"Google, LLC"}]},{"given":"Yanzhang","family":"He","sequence":"additional","affiliation":[{"name":"Google, LLC"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2846"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7953075"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003906"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1855"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref10","article-title":"Speechstew: Simply mix all available speech recognition data to train one large neural network","author":"Chan","year":"2021","journal-title":"arXiv preprint arXiv:2104.02133"},{"key":"ref11","article-title":"Google usm: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2303.01037"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10809"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1962"},{"key":"ref14","article-title":"A simplified fully quantized transformer for end-to-end speech recognition","author":"Bie","year":"2019","journal-title":"arXiv preprint arXiv:1911.03604"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747552"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1012"},{"key":"ref17","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022","journal-title":"arXiv preprint arXiv:2212.04356"},{"key":"ref18","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2023","journal-title":"arXiv preprint arXiv:2305.13516"},{"key":"ref19","first-page":"7197","article-title":"Up or down? adaptive rounding for post-training quantization","volume-title":"International Conference on Machine Learning","author":"Nagel"},{"key":"ref20","article-title":"Improving post training neural quantization: Layer-wise calibration and integer programming","author":"Hubara","year":"2020","journal-title":"arXiv preprint arXiv:2006.10518"},{"key":"ref21","article-title":"Optimal brain compression: A framework for accurate post-training quantization and pruning","author":"Frantar","year":"2022","journal-title":"arXiv preprint arXiv:2208.11580"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref23","article-title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","author":"Saxe","year":"2013","journal-title":"arXiv preprint arXiv:1312.6120"},{"key":"ref24","article-title":"All you need is a good init","author":"Jiri Matas","year":"2015","journal-title":"arXiv preprint arXiv:1511.06422"},{"key":"ref25","first-page":"3570","article-title":"On orthogonality and learning recurrent networks with long term dependencies","volume-title":"International Conference on Machine Learning","author":"Vorontsov"},{"key":"ref26","article-title":"Full-capacity unitary recurrent neural networks","volume":"29","author":"Wisdom","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.48"},{"key":"ref28","article-title":"Can we gain more from orthogonality regularizations in training deep networks?","volume":"31","author":"Bansal","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","first-page":"854","article-title":"Parseval networks: Improving robustness to adversarial examples","volume-title":"International conference on machine learning","author":"Cisse"},{"key":"ref30","article-title":"Reducing overfitting in deep networks by decorrelating representations","author":"Cogswell","year":"2015","journal-title":"arXiv preprint arXiv:1511.06068"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141267"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00844"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.410"},{"article-title":"Learned step size quantization","volume-title":"International Conference on Learning Representations","author":"Esser","key":"ref34"},{"journal-title":"Transactions on Machine Learning Research","article-title":"Differentiable model compression via pseudo quantization noise","author":"D\u00e9fossez","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3390\/math9172144"},{"key":"ref37","article-title":"Rand: Robustness aware norm decay for quantized seq2seq models","author":"Qiu","year":"2023","journal-title":"arXiv preprint arXiv:2305.15536"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2006.871582"},{"key":"ref39","first-page":"1","article-title":"Automatic differentiation in machine learning: a survey","volume":"18","author":"Baydin","year":"2018","journal-title":"Journal of Marchine Learning Research"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2005.858979"},{"key":"ref42","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv:1412.6980"},{"key":"ref43","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2023,12,16]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389686.pdf?arnumber=10389686","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T11:36:09Z","timestamp":1706009769000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389686\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389686","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}