{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:16:04Z","timestamp":1776442564865,"version":"3.51.2"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889116","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["MSA-ASR: Efficient Multilingual Speaker Attribution with frozen ASR Models"],"prefix":"10.1109","author":[{"given":"Thai-Binh","family":"Nguyen","sequence":"first","affiliation":[{"name":"Karlsruhe Institute of Technology,Karlsruhe,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Waibel","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pennsylvania,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/319463.319484"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2000.871074"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/971478.971505"},{"key":"ref4","article-title":"Estimating focus of attention based on gaze and sound","volume-title":"Workshop on Perceptive User Interfaces","author":"S"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-93808-0_40"},{"key":"ref6","article-title":"Simultaneous translation of open domain lectures and speeches","volume-title":"uS Patent","author":"Waibel","year":"2012"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383556"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687974"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2024-15"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11210"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10626098"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383600"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746225"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-253"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389762"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-101"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-601"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447957"},{"key":"ref19","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5743675"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.2002-409"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1493"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446589"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094928"},{"key":"ref25","first-page":"3264","article-title":"Overlaps and gender analysis in the context of broadcast media","volume-title":"Proceedings of the Thirteenth Language Resources and Evaluation Conference","author":"Lebourdais"},{"key":"ref26","article-title":"Detecting double-talk (overlapping speech) in conversations using deep learning","author":"Abdullah","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2671"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59430-5_11"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746806"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-105"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref36","article-title":"Silero vad: pre-trained enterprise-grade voice activity detector (vad), number detector and language classifier","year":"2021"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889116.pdf?arnumber=10889116","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:23Z","timestamp":1774416203000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889116\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889116","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}