{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T15:01:28Z","timestamp":1784214088340,"version":"3.55.0"},"reference-count":20,"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\/icassp43922.2022.9747755","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"4298-4302","source":"Crossref","is-referenced-by-count":28,"title":["Noise-Robust Speech Recognition With 10 Minutes Unparalleled In-Domain Data"],"prefix":"10.1109","author":[{"given":"Chen","family":"Chen","sequence":"first","affiliation":[{"name":"Nanyang Technological University,School of Computer Science and Engineering,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nana","family":"Hou","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,School of Computer Science and Engineering,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuchen","family":"Hu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,School of Computer Science and Engineering,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shashank","family":"Shirol","sequence":"additional","affiliation":[{"name":"Manipal Institute of Technology,Manipal,India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eng Siong","family":"Chng","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,School of Computer Science and Engineering,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023218"},{"key":"ref12","first-page":"319","article-title":"Contrastive learning for unpaired image-to-image translation","author":"park","year":"2020","journal-title":"European Conference on Computer Vision"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413512"},{"key":"ref14","first-page":"3733","article-title":"Unsupervised feature learning via non-parametric instance discrimination","author":"wu","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref15","first-page":"1970","article-title":"The rats collection: Supporting hlt research with degraded audio data","author":"graff","year":"2014","journal-title":"LREC"},{"key":"ref16","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref17","article-title":"Multitask-based joint learning approach to robust asr for radio communication speech","author":"ma","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462624"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023316"},{"key":"ref5","article-title":"Roles of pre-training and fine-tuning in context-dependent dbn-hmms for realworld speech recognition","author":"yu","year":"2010","journal-title":"Proc NIPS Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref7","article-title":"Generative adversarial nets","volume":"27","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref1","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"hannun","year":"2014"},{"key":"ref9","first-page":"1125","article-title":"Imageto-image translation with conditional adversarial networks","author":"isola","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"}],"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\/09747755.pdf?arnumber=9747755","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:11:32Z","timestamp":1661199092000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747755\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747755","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}