{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T16:50:46Z","timestamp":1770742246067,"version":"3.49.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747374","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"3179-3183","source":"Crossref","is-referenced-by-count":12,"title":["An Adapter Based Pre-Training for Efficient and Scalable Self-Supervised Speech Representation Learning"],"prefix":"10.1109","author":[{"given":"Samuel","family":"Kessler","sequence":"first","affiliation":[{"name":"University of Oxford"}]},{"given":"Bethan","family":"Thomas","sequence":"additional","affiliation":[{"name":"Huawei R&D UK"}]},{"given":"Salah","family":"Karout","sequence":"additional","affiliation":[{"name":"Huawei R&D UK"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref11","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"2016"},{"key":"ref12","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","author":"maddison","year":"2016"},{"key":"ref13","article-title":"Learning multiple visual domains with residual adapters","author":"rebuffi","year":"2017"},{"key":"ref14","article-title":"Adapterfusion: Non-destructive task composition for transfer learning","author":"pfeiffer","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.617"},{"key":"ref16","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref17","article-title":"Pretrained transformers as universal computation engines","author":"lu","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref4","article-title":"wav2vec: Unsupervised pretraining for speech recognition","author":"schneider","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref5","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01294-2"},{"key":"ref7","article-title":"Attention is all you need","author":"vaswani","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref1","article-title":"Representation learning with contrastive predictive coding","author":"den oord","year":"2018"},{"key":"ref9","first-page":"2790","article-title":"Parameter-efficient transfer learning for nlp","author":"houlsby","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref22","article-title":"Common voice: A massively-multilingual speech corpus","author":"ardila","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref24","first-page":"3987","article-title":"Continual learning through synaptic intelligence","author":"zenke","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"kirkpatrick","year":"2017","journal-title":"Proceedings of the National Academy of Sciences"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747374.pdf?arnumber=9747374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:10:05Z","timestamp":1660594205000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747374\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747374","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}