{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:17:52Z","timestamp":1776442672571,"version":"3.51.2"},"reference-count":30,"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\/icassp48485.2024.10446589","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10461-10465","source":"Crossref","is-referenced-by-count":5,"title":["Synthetic Conversations Improve Multi-Talker ASR"],"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","article-title":"Librimix: An open-source dataset for generalizable speech separation","author":"Cosentino","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383556"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097139"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095295"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878256"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101317"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746531"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1943"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-102"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref14","article-title":"MuST-C: a Multilingual Speech Translation Corpus","volume-title":"NAACL","author":"Gangi"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref17","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"LREC","author":"Ardila"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-560"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1896"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3074"},{"key":"ref22","article-title":"Scaling speech technology to 1, 000+ languages","author":"Pratap","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1162"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref26","article-title":"The kaldi speech recognition toolkit","volume-title":"ASRU","author":"Povey"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1449"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1276"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383600"},{"key":"ref30","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"}],"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\/10446589.pdf?arnumber=10446589","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:21:49Z","timestamp":1722576109000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446589\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446589","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}