{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T05:07:12Z","timestamp":1737176832194,"version":"3.33.0"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832205","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"1023-1030","source":"Crossref","is-referenced-by-count":0,"title":["Rand: Robustness Aware Norm Decay for Quantized Neural Networks"],"prefix":"10.1109","author":[{"given":"David","family":"Qiu","sequence":"first","affiliation":[{"name":"Google, LLC"}]},{"given":"David","family":"Rim","sequence":"additional","affiliation":[{"name":"Google, LLC"}]},{"given":"Shaojin","family":"Ding","sequence":"additional","affiliation":[{"name":"Google, LLC"}]},{"given":"Oleg","family":"Rybakov","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":"10.3390\/sym11081018"},{"key":"ref2","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"Hannun","year":"2014","journal-title":"arXiv preprint arXiv:1412.5567"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1211.3711"},{"key":"ref4","first-page":"577","article-title":"Attention-based models for speech recognition","author":"Chorowski","year":"2015","journal-title":"ICONIP"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2846"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8682336"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003906"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1855"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00345"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1991"},{"key":"ref14","article-title":"Quantization of acoustic model parameters in automatic speech recognition framework","author":"Prasad","year":"2020","journal-title":"arXiv preprint arXiv:2006.09054"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10809"},{"key":"ref16","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013","journal-title":"arXiv preprint arXiv:1308.3432"},{"key":"ref17","article-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or -1","author":"Courbariaux","year":"2016","journal-title":"arXiv preprint arXiv:1602.02830"},{"key":"ref18","first-page":"16318","article-title":"Overcoming oscillations in quantization-aware training","volume-title":"International Conference on Machine Learning.","author":"Nagel"},{"article-title":"Learned step size quantization","volume-title":"International Conference on Learning Representations","author":"Esser","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/math9172144"},{"key":"ref21","first-page":"112","article-title":"Trained quantization thresholds for accurate and efficient fixed-point inference of deep neural networks","volume-title":"Proceedings of Machine Learning and Systems","volume":"2","author":"Jain"},{"key":"ref22","article-title":"Nipq: Noise injection pseudo quantization for automated dnn optimization","author":"Park","year":"2022","journal-title":"arXiv preprint arXiv:2206.00820"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5555\/2986459.2986721"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/19.492748"},{"key":"ref25","first-page":"12367","article-title":"Universally quantized neural compression","volume":"33","author":"Agustsson","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref26","article-title":"Visualizing the loss landscape of neural nets","volume":"31","author":"Li","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref27","first-page":"23439","article-title":"Sharpness-aware training for free","volume":"35","author":"Du","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"Han","year":"2015","journal-title":"arXiv preprint arXiv:1510.00149"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-128"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9747552"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054188"},{"key":"ref32","first-page":"7197","article-title":"Up or down? adaptive rounding for post-training quantization","volume-title":"International Conference on Machine Learning.","author":"Nagel"},{"key":"ref33","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":"ref34","article-title":"Optimal brain compression: A framework for accurate post-training quantization and pruning","author":"Frantar","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414920"},{"key":"ref37","article-title":"Differentiable model compression via pseudo quantization noise","author":"D\u00b4efossez","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref38","article-title":"Training with quantization noise for extreme model compression","author":"Fan","year":"2020","journal-title":"arXiv preprint arXiv:2004.07320"},{"key":"ref39","article-title":"Error-aware quantization through noise tempering","author":"Wang","year":"2022","journal-title":"arXiv preprint arXiv:2212.05603"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3444943"},{"key":"ref41","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014","journal-title":"arXiv preprint arXiv:1412.6572"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref43","first-page":"1","article-title":"The ami meeting corpus","volume-title":"Proc. International Conference on Methods and Techniques in Behavioral Research","author":"Kraaij"},{"key":"ref44","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2019","journal-title":"arXiv preprint arXiv:1912.06670"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref46","first-page":"125","article-title":"Tedlium: an automatic speech recognition dedicated corpus","author":"Rousseau","year":"2012","journal-title":"LREC"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"ref48","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":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10791"},{"key":"ref51","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv:1412.6980"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-2012"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2024,12,2]]},"location":"Macao","end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832205.pdf?arnumber=10832205","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:41:55Z","timestamp":1737099715000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832205\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832205","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}