{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:13:57Z","timestamp":1776885237711,"version":"3.51.2"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447834","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10931-10935","source":"Crossref","is-referenced-by-count":5,"title":["Joint Unsupervised and Supervised Training for Automatic Speech Recognition via Bilevel Optimization"],"prefix":"10.1109","author":[{"given":"A F M","family":"Saif","sequence":"first","affiliation":[{"name":"Rensselaer Polytechnic Institute,Troy,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodong","family":"Cui","sequence":"additional","affiliation":[{"name":"IBM Research AI,T. J. Watson Research Center,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Shen","sequence":"additional","affiliation":[{"name":"Rensselaer Polytechnic Institute,Troy,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Songtao","family":"Lu","sequence":"additional","affiliation":[{"name":"IBM Research AI,T. J. Watson Research Center,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian","family":"Kingsbury","sequence":"additional","affiliation":[{"name":"IBM Research AI,T. J. Watson Research Center,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyi","family":"Chen","sequence":"additional","affiliation":[{"name":"Rensselaer Polytechnic Institute,Troy,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Baevski","year":"2019","journal-title":"vq-wav2vec: Self-supervised learning of discrete speech representations"},{"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":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746038"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1137\/16m1080173"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s13675-020-00122-z"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1561\/2000000115"},{"key":"ref7","first-page":"2466","article-title":"A single-timescale method for stochastic bilevel optimization","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Chen"},{"key":"ref8","first-page":"3915","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"International Conference on Machine Learning","author":"Chiu"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1561\/2000000111"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-52119-6"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639344"},{"key":"ref12","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"International Conference on Machine Learning","author":"Finn"},{"key":"ref13","first-page":"1568","article-title":"Bilevel programming for hyperparameter optimization and meta-learning","volume-title":"International Conference on Machine Learning","author":"Franceschi"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2021.12.009"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132674"},{"key":"ref20","author":"Loshchilov","year":"2017","journal-title":"Decoupled weight decay regularization"},{"key":"ref21","first-page":"22758","article-title":"Bilevel optimization with coupled decision-dependent distributions","volume-title":"International Conference on Machine Learning","author":"Lu"},{"key":"ref22","author":"van den Oord","year":"2018","journal-title":"Representation learning with contrastive predictive coding"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref26","first-page":"737","article-title":"Hyperparameter optimization with approximate gradient","volume-title":"International Conference on Machine Learning","author":"Pedregosa"},{"issue":"3","key":"ref27","article-title":"To transfer or not to transfer","volume-title":"NIPS workshop on transfer learning","author":"Rosenstein"},{"key":"ref28","first-page":"3935","article-title":"Enhancing the ted-lium corpus with selected data for language modeling and more ted talks","volume-title":"The International Conference on Language Resources and Evaluation","author":"Rousseau"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1137\/16M105592X"},{"key":"ref30","author":"Shen","year":"2023","journal-title":"On penalty-based bilevel gradient descent method"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/BF01096458"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01155"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447834.pdf?arnumber=10447834","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:35:24Z","timestamp":1722573324000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447834\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447834","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}