{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:39:02Z","timestamp":1730230742572,"version":"3.28.0"},"reference-count":23,"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\/icassp49357.2023.10094726","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":2,"title":["Data2vec-Aqc: Search for the Right Teaching Assistant in the Teacher-Student Training Setup"],"prefix":"10.1109","author":[{"given":"Vasista Sai","family":"Lodagala","sequence":"first","affiliation":[{"name":"Indian Institute of Technology,Madras,India"}]},{"given":"Sreyan","family":"Ghosh","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,USA"}]},{"given":"S.","family":"Umesh","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology,Madras,India"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref12","first-page":"21271","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","volume":"33","year":"0","journal-title":"NeurIPS 2020"},{"key":"ref23","article-title":"The design for the wall street journal-based csr corpus","author":"paul","year":"1992","journal-title":"Speech and Natural Language Proceedings of a Workshop Held at Harriman"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"den oord","key":"ref15"},{"article-title":"Speech simclr: Combining contrastive and reconstruction objective for self-supervised speech representation learning","year":"2020","author":"jiang","key":"ref14"},{"article-title":"MU-SAN: A Music, Speech, and Noise Corpus","year":"2015","author":"snyder","key":"ref20"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"article-title":"Ressl: Relational self-supervised learning with weak augmentation","year":"2021","author":"zheng","key":"ref22"},{"article-title":"Ccc-wav2vec 2.0: Clustering aided cross contrastive self-supervised learning of speech representations","year":"2022","author":"lodagala","key":"ref10"},{"article-title":"Improving noise robustness of an end-to-end neural model for automatic speech recognition","year":"2020","author":"balam","key":"ref21"},{"key":"ref2","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"0","journal-title":"NeurIPS 2020"},{"article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","year":"2022","author":"baevski","key":"ref1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref16","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"0","journal-title":"ICML 2020"},{"key":"ref19","article-title":"Switch-board: telephone speech corpus for research and development","author":"godfrey","year":"0","journal-title":"ICASSP 1992"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"article-title":"Measuring the impact of individual domain factors in self-supervised pre-training","year":"2022","author":"sanabria","key":"ref7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-667"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"article-title":"The history of speech recognition to the year 2030","year":"2021","author":"hannun","key":"ref5"}],"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\/10094726.pdf?arnumber=10094726","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T14:09:05Z","timestamp":1700489345000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094726\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094726","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}