{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:37:41Z","timestamp":1783183061563,"version":"3.54.6"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095780","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":32,"title":["Structured Pruning of Self-Supervised Pre-Trained Models for Speech Recognition and Understanding"],"prefix":"10.1109","author":[{"given":"Yifan","family":"Peng","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,PA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kwangyoun","family":"Kim","sequence":"additional","affiliation":[{"name":"ASAPP Inc.,Mountain View,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix","family":"Wu","sequence":"additional","affiliation":[{"name":"ASAPP Inc.,Mountain View,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prashant","family":"Sridhar","sequence":"additional","affiliation":[{"name":"ASAPP Inc.,Mountain View,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,PA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref35","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref12","article-title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","author":"sanh","year":"2019"},{"key":"ref34","article-title":"Learning Sparse Neural Networks through L0 Regularization","author":"louizos","year":"2018","journal-title":"ICLRE"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747490"},{"key":"ref37","article-title":"TED-LIUM: an automatic speech recognition dedicated corpus","author":"rousseau","year":"2012","journal-title":"Proc LREC"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.sustainlp-1.14"},{"key":"ref36","article-title":"Huggingface’s transformers: State-of-the-art natural language processing","author":"wolf","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747432"},{"key":"ref11","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015"},{"key":"ref33","article-title":"Gaussian Error Linear Units (GELUs)","author":"hendrycks","year":"2016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref32","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11112"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.588"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10269"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref19","article-title":"Pruning Filters for Efficient ConvNets","author":"li","year":"2017","journal-title":"Proc ICLR"},{"key":"ref18","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"2015","journal-title":"Proc NeurIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.510"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.107"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2917312"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218499"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11441"},{"key":"ref41","article-title":"Branch-former: Parallel MLP-attention architectures to capture local and global context for speech recognition and understanding","author":"peng","year":"2022","journal-title":"Proc ICML"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.496"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"ref21","article-title":"PLATON: Pruning large transformer models with upper confidence bound of weight importance","author":"zhang","year":"2022","journal-title":"Proc ICML"},{"key":"ref43","article-title":"Wav2seq: Pre-training speech-to-text encoder-decoder models using pseudo languages","author":"wu","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.02.029"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413536"},{"key":"ref29","article-title":"PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition","author":"lai","year":"2021","journal-title":"Proc NeurIPS"},{"key":"ref8","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref7","article-title":"A Study on the Integration of Pre-trained SSL, ASR, LM and SLU Models for Spoken Language Understanding","author":"peng","year":"2022","journal-title":"Proc SLT"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746303"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688137"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747674"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746137"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383521"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095780.pdf?arnumber=10095780","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:00:49Z","timestamp":1699902049000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095780\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095780","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}