{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T07:53:51Z","timestamp":1760255631869,"version":"3.37.3"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"SERB-Startup Research","award":["SRG\/2021\/002348"],"award-info":[{"award-number":["SRG\/2021\/002348"]}]},{"DOI":"10.13039\/501100007296","name":"Infosys Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007296","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3463430","type":"journal-article","created":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T17:26:21Z","timestamp":1726853181000},"page":"4226-4236","source":"Crossref","is-referenced-by-count":1,"title":["On the Quantization of Neural Models for Speaker Verification"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1549-6350","authenticated-orcid":false,"given":"Vishal","family":"Kumar","sequence":"first","affiliation":[{"name":"Infosys Centre for AI and CSE Department, Indraprastha Institute of Information Technology Delhi, New Delhi, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8149-8151","authenticated-orcid":false,"given":"Vinayak","family":"Abrol","sequence":"additional","affiliation":[{"name":"Infosys Centre for AI and CSE Department, Indraprastha Institute of Information Technology Delhi, New Delhi, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8714-1409","authenticated-orcid":false,"given":"Mathew","family":"Magamai Doss","sequence":"additional","affiliation":[{"name":"Idiap Research Institute, Martigny, Switzerland"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Binarized neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hubara","year":"2016"},{"key":"ref2","first-page":"12546","article-title":"Differentiable dynamic quantization with mixed precision and adaptive resolution","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00522"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3210297"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01544"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref8","first-page":"30318","article-title":"GPT3.int8(): 8-bit matrix multiplication for transformers at scale","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dettmers","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3301007"},{"article-title":"GitHub repository","year":"2020","author":"Peri","key":"ref10"},{"key":"ref11","first-page":"4475","article-title":"Optimal brain compression: A framework for accurate post-training quantization and pruning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Frantar","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-126"},{"key":"ref14","first-page":"1","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Han","year":"2016"},{"key":"ref15","first-page":"1","article-title":"Resurrecting the sigmoid in deep learning through dynamical isometry: Theory and practice","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pennington","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2021.12.010"},{"key":"ref17","first-page":"1","article-title":"Learned step size quantization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Esser","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1524"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2019.00127"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00356"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00100"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746806"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/a16010031"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3264558"},{"key":"ref25","first-page":"1","article-title":"Understanding straight-through estimator in training activation quantized neural nets","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yin","year":"2019"},{"article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","year":"2013","author":"Bengio","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00448"},{"key":"ref28","first-page":"112","article-title":"Trained quantization thresholds for accurate and efficient fixed-point inference of deep neural networks","volume-title":"Proc. Mach. Learn. Syst. Conf.","author":"Jain","year":"2020"},{"key":"ref29","first-page":"19123","article-title":"Optimal clipping and magnitude-aware differentiation for improved quantization-aware training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sakr","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17269"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"ref32","first-page":"18518","article-title":"HAWQ-V2: Hessian aware trace-weighted quantization of neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dong","year":"2020"},{"key":"ref33","first-page":"9295","article-title":"SDQ: Stochastic differentiable quantization with mixed precision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00215"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2886192"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16839"},{"key":"ref37","first-page":"1","article-title":"Apprentice: Using knowledge distillation techniques to improve low-precision network accuracy","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mishra","year":"2018"},{"key":"ref38","first-page":"1","article-title":"Model compression via distillation and quantization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Polino","year":"2018"},{"key":"ref39","first-page":"14","article-title":"Restructuring batch normalization to accelerate CNN training","volume-title":"Proc. Mach. Learn. Syst.","author":"Jung","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683760"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00815"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10684732.pdf?arnumber=10684732","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:29:54Z","timestamp":1727717394000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10684732\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3463430","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2024]]}}}