{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T07:03:25Z","timestamp":1760598205046,"version":"3.37.3"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key RD Program of China","doi-asserted-by":"publisher","award":["2018AAA0101100"],"award-info":[{"award-number":["2018AAA0101100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61832008,62072367"],"award-info":[{"award-number":["61832008,62072367"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892465","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["LRTD: A Low-rank Transformer with Dynamic Depth and Width for Speech Recognition"],"prefix":"10.1109","author":[{"given":"Fan","family":"Yu","sequence":"first","affiliation":[{"name":"Xi'an Jiaotong University School of Computer Science&Technology,Xi'an,China"}]},{"given":"Wei","family":"Xi","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University School of Computer Science&Technology,Xi'an,China"}]},{"given":"Zhao","family":"Yang","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University School of Computer Science&Technology,Xi'an,China"}]},{"given":"Ziye","family":"Tong","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University School of Computer Science&Technology,Xi'an,China"}]},{"given":"Jingtong","family":"Sun","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University School of Software Engineering,Xi'an,China"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref32","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref31","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.537"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1117"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref11","volume":"abs 2009 6732","author":"tay","year":"2020","journal-title":"Efficient transformers A survey"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053878"},{"key":"ref13","first-page":"546","article-title":"Self-distillation for improving etc-transformer-based ASR systems","author":"moriya","year":"0","journal-title":"Annual Conference of the International Speech Communication Association"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054724"},{"key":"ref15","article-title":"Reducing transformer depth on demand with structured dropout","author":"fan","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.178"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-233"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref28","volume":"abs 1602 7360","author":"iandola","year":"2016","journal-title":"SqueezeNet AlexNet-level accuracy with 50x fewer parameters and"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003906"},{"key":"ref6","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"0","journal-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems"},{"key":"ref29","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","author":"lan","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2933146"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref7","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems"},{"key":"ref2","volume":"abs 1211 3711","author":"graves","year":"2012","journal-title":"Sequence transduction with recurrent neural networks"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054345"},{"key":"ref1","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume":"32","author":"graves","year":"0","journal-title":"Proceedings of the 31th International Conference on Machine Learning"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60276-5_22"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.287"},{"key":"ref24","article-title":"On the effectiveness of lowrank matrix factorization for 1stm model compression","author":"winata","year":"0","journal-title":"Proceedings of the 33rd Pacific Asia Conference on Language Information and Computation"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2975987"},{"key":"ref26","first-page":"3123","article-title":"Binaryconnect: Training deep neural networks with binary weights during propagations","author":"courbariaux","year":"0","journal-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems"},{"key":"ref25","volume":"abs 1503 2531","author":"hinton","year":"2015","journal-title":"Distilling the knowledge in a neural network"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2022,7,18]]},"location":"Padua, Italy","end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892465.pdf?arnumber=9892465","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T22:59:36Z","timestamp":1667516376000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892465\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892465","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}