{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:37:35Z","timestamp":1767339455221,"version":"3.28.0"},"reference-count":21,"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\/icasspw59220.2023.10193371","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T13:30:54Z","timestamp":1690983054000},"page":"1-5","source":"Crossref","is-referenced-by-count":7,"title":["Improving Label-Deficient Keyword Spotting Through Self-Supervised Pretraining"],"prefix":"10.1109","author":[{"given":"Holger Severin","family":"Bovbjerg","sequence":"first","affiliation":[{"name":"Aalborg University,Department of Electronic Systems,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng-Hua","family":"Tan","sequence":"additional","affiliation":[{"name":"Aalborg University,Department of Electronic Systems,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","author":"baevski","year":"2022","journal-title":"Proceedings of the 39th International Conference on Machine Learning"},{"key":"ref12","first-page":"344","article-title":"Audio albert: A lite bert for self-supervised learning of audio representation","author":"chi","year":"2020","journal-title":"2021 IEEE Spoken Language TechnologyWorkshop (SLT)"},{"key":"ref15","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","volume":"abs 1804 3209","author":"warden","year":"2018","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1286"},{"key":"ref20","article-title":"Adam: A method for stochastic optimization","volume":"abs 1412 6980","author":"kingma","year":"2014","journal-title":"CoRR"},{"key":"ref11","article-title":"On the efficacy of small self-supervised contrastive models without distillation signals","author":"shi","year":"2021","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref10","article-title":"Big self-supervised models are strong semi-supervised learners","volume":"33","author":"chen","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Super-convergence: very fast training of neural networks using large learning rates","author":"smith","year":"2017","journal-title":"Defense and Commercial Sensing"},{"key":"ref2","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3139508"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref16","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume":"abs 2010 11929","author":"dosovitskiy","year":"2020","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref18","article-title":"Fixing weight decay regularization in adam","volume":"abs 1711 5101","author":"loshchilov","year":"2017","journal-title":"CoRR"},{"key":"ref8","article-title":"Simple distillation baselines for improving small self-supervised models","volume":"abs 2106 11304","author":"gu","year":"2021","journal-title":"CoRR"},{"key":"ref7","article-title":"Distilling the knowledge in a neural network","volume":"abs 1503 2531","author":"hinton","year":"2015","journal-title":"ArXiv"},{"key":"ref9","article-title":"SEED: self-supervised distillation for visual representation","volume":"abs 2101 4731","author":"fang","year":"2021","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"}],"event":{"name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10192576\/10192577\/10193371.pdf?arnumber=10193371","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T13:42:36Z","timestamp":1692625356000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10193371\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icasspw59220.2023.10193371","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}