{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:00:59Z","timestamp":1764403259886},"reference-count":29,"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\/icassp49357.2023.10095929","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["Self-Supervised Speech Representation Learning for Keyword-Spotting With Light-Weight Transformers"],"prefix":"10.1109","author":[{"given":"Chenyang","family":"Gao","sequence":"first","affiliation":[{"name":"The State University of New Jersey,Rutgers"}]},{"given":"Yue","family":"Gu","sequence":"additional","affiliation":[{"name":"Amazon,Alexa Perceptual Technologies"}]},{"given":"Francesco","family":"Caliva","sequence":"additional","affiliation":[{"name":"Amazon,Alexa Perceptual Technologies"}]},{"given":"Yuzong","family":"Liu","sequence":"additional","affiliation":[{"name":"Amazon,Alexa Perceptual Technologies"}]}],"member":"263","reference":[{"key":"ref13","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref12","article-title":"Deep contextualized acoustic representations for semisupervised speech recognition","author":"ling","year":"2020","journal-title":"ICASSP"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"article-title":"Decoar 2.0: Deep contextualized acoustic representations with vector quantization","year":"2020","author":"ling","key":"ref14"},{"key":"ref11","article-title":"Representation learning with contrastive predictive coding","author":"den oord","year":"2018","journal-title":"NeurIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747490"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref1","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL"},{"article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","year":"2022","author":"baevski","key":"ref17"},{"article-title":"Improving label-deficient keyword spotting using self-supervised pretraining","year":"2022","author":"bovbjerg","key":"ref16"},{"key":"ref19","article-title":"Product quantization for nearest neighbor search","author":"jegou","year":"2010","journal-title":"IEEE PAMI"},{"article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","year":"2018","author":"warden","key":"ref18"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747077"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688299"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref20","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"2017","journal-title":"ICLRE"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"simonyan","key":"ref22"},{"key":"ref21","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref28"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"article-title":"Extracting speaker and emotion information from self-supervised speech models via channel-wise correlations","year":"2022","author":"stafylakis","key":"ref29"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"article-title":"Improving transformer-based speech recognition using unsupervised pre-training","year":"2019","author":"jiang","key":"ref7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054438"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","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\/10095929.pdf?arnumber=10095929","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T14:10:55Z","timestamp":1700489455000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095929\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095929","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}