{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T21:26:49Z","timestamp":1775597209938,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10022821","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"15-22","source":"Crossref","is-referenced-by-count":8,"title":["Sub-8-Bit Quantization for On-Device Speech Recognition: A Regularization-Free Approach"],"prefix":"10.1109","author":[{"given":"Kai","family":"Zhen","sequence":"first","affiliation":[{"name":"Amazon Alexa AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Radfar","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hieu","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Grant P.","family":"Strimel","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nathan","family":"Susanj","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Athanasios","family":"Mouchtaris","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Brecq: Pushing the limit of post-training quantization by block reconstruction","author":"Li","year":"2021","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Post-training quantization for vision transformer","volume":"34","author":"Liu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-06053-z"},{"key":"ref4","first-page":"9847","article-title":"Towards accurate post-training network quantization via bit-split and stitching","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1962"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747552"},{"key":"ref7","first-page":"265","article-title":"TensorFlow: A System for Large-Scale Machine Learning","volume-title":"12th USENIX symposium on operating systems design and implementation (OSDI 16)","author":"Abadi","year":"2016"},{"key":"ref8","article-title":"Neural Network Quantization with AI Model Efficiency Toolkit (AIMET)","author":"Siddegowda","year":"2022","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10809"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414076"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/EMC2-NIPS53020.2019.00016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1991"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-874"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-50"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268935"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414652"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413899"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747879"},{"key":"ref20","article-title":"AutoQ: Automated kernel-wise neural network quantization","author":"Lou","year":"2019","journal-title":"arXiv preprint"},{"key":"ref21","first-page":"800","article-title":"Tensorflow lite micro: Embedded machine learning for tinyml systems","volume-title":"Proceedings of Machine Learning and Systems","volume":"3","author":"David","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01544"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0265621"},{"key":"ref24","article-title":"Soft-to-hard vector quantization for end-to-end learning compressible representations","volume":"30","author":"Agustsson","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1816"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10084"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632723"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1204"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1970.tb01843.x"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref33","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref34","volume-title":"ONNX: Open Neural Network Exchange","author":"Bai","year":"2019"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","location":"Doha, Qatar","start":{"date-parts":[[2023,1,9]]},"end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10022821.pdf?arnumber=10022821","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T06:10:34Z","timestamp":1707804634000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022821\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022821","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}