{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:20:49Z","timestamp":1753600849562},"reference-count":26,"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\/icasspw62465.2024.10626098","type":"proceedings-article","created":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T17:19:18Z","timestamp":1723742358000},"page":"565-569","source":"Crossref","is-referenced-by-count":1,"title":["ConVoiFilter: A Case Study of Doing Cocktail Party Speech Recognition"],"prefix":"10.1109","author":[{"given":"Thai-Binh","family":"Nguyen","sequence":"first","affiliation":[{"name":"Karlsruhe Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Waibel","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1114"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/319463.319484"},{"key":"ref3","first-page":"32","article-title":"Multimodal meeting tracker","volume-title":"RIAO","author":"Bett"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003785"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-1-84882-054-8_1","volume-title":"Computers in the Human Interaction Loop","author":"Waibel","year":"2009"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84882-054-8_30"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3018668"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1205"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462661"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1193"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59430-5_11"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"NeurIPS 2020","author":"Baevski","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1768"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"article-title":"MUSAN: A Music, Speech, and Noise Corpus","year":"2015","author":"Snyder","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2917582"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"article-title":"Robust speech recognition via large-scale weak supervision","year":"2022","author":"Radford","key":"ref26"}],"event":{"name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10625769\/10625780\/10626098.pdf?arnumber=10626098","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T05:51:22Z","timestamp":1723787482000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10626098\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icasspw62465.2024.10626098","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}