{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:09:10Z","timestamp":1776881350397,"version":"3.51.2"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2046963"],"award-info":[{"award-number":["2046963"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1109\/waspaa52581.2021.9632771","type":"proceedings-article","created":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T21:12:28Z","timestamp":1639429948000},"page":"176-180","source":"Crossref","is-referenced-by-count":19,"title":["Test-Time Adaptation Toward Personalized Speech Enhancement: Zero-Shot Learning with Knowledge Distillation"],"prefix":"10.1109","author":[{"given":"Sunwoo","family":"Kim","sequence":"first","affiliation":[{"name":"Indiana University,Department of Intelligent Systems Engineering,Bloomington,IN,USA,47408"}]},{"given":"Minje","family":"Kim","sequence":"additional","affiliation":[{"name":"Indiana University,Department of Intelligent Systems Engineering,Bloomington,IN,USA,47408"}]}],"member":"263","reference":[{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"ref10","article-title":"Zero-shot learning for semantic utterance classification","author":"dauphin","year":"0","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"ref11","article-title":"Zero-shot learning for audio-based music classification and tagging","author":"choi","year":"0","journal-title":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2989"},{"key":"ref13","article-title":"Zero-shot personalized speech enhancement through speaker-informed model selection","year":"0","journal-title":"Proceedings of the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"},{"key":"ref14","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00361"},{"key":"ref16","article-title":"Data-free knowledge distillation for deep neural networks","author":"lopes","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref17","first-page":"4743","article-title":"Zero-shot knowledge distillation in deep networks","author":"nayak","year":"0","journal-title":"Proceedings of the International Conference on Machine Learning (ICML)"},{"key":"ref18","first-page":"695","article-title":"Unsuper-vised training of a deep clustering model for multichannel blind source separation","author":"drude","year":"0","journal-title":"Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref19","first-page":"81","article-title":"Unsuper-vised deep clustering for source separation: Direct learning from mixtures using spatial information","author":"tzinis","year":"0","journal-title":"Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.11.063"},{"key":"ref27","first-page":"626","article-title":"SDR - half-baked or well done?","author":"le roux","year":"0","journal-title":"ICASSP 2019–2019 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2324759"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3293318"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1673"},{"key":"ref5","article-title":"Self-Supervised Learning for Personalized Speech Enhancement","author":"sivaraman","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref8","first-page":"3","article-title":"Zero-data learning of new tasks","volume":"1","author":"larochelle","year":"0","journal-title":"Proceedings of the AAAI National Conference on Artificial Intelligence (AAAI)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2857768"},{"key":"ref2","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"han","year":"0","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"ref9","article-title":"Zero-shot learning with semantic output codes","author":"palatucci","year":"2009","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-519"},{"key":"ref22","first-page":"5206","article-title":"Lib-rispeech: An ASR corpus based on public domain audio books","author":"panayotov","year":"0","journal-title":"Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref23","article-title":"MUSAN: A Music, Speech, and Noise Corpus","author":"snyder","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"}],"event":{"name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","location":"New Paltz, NY, USA","start":{"date-parts":[[2021,10,17]]},"end":{"date-parts":[[2021,10,20]]}},"container-title":["2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9632687\/9632666\/09632771.pdf?arnumber=9632771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:57:41Z","timestamp":1659484661000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9632771\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/waspaa52581.2021.9632771","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]}}}