{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:23:04Z","timestamp":1774419784006,"version":"3.50.1"},"reference-count":39,"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\/icassp49660.2025.10888138","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Speech Data Selection for Efficient ASR Fine-Tuning using Domain Classifier and Pseudo-Label Filtering"],"prefix":"10.1109","author":[{"given":"Pradeep","family":"Rangappa","sequence":"first","affiliation":[{"name":"Idiap Research Institute,Martigny,Switzerland"}]},{"given":"Juan","family":"Zuluaga-Gomez","sequence":"additional","affiliation":[{"name":"Idiap Research Institute,Martigny,Switzerland"}]},{"given":"Srikanth","family":"Madikeri","sequence":"additional","affiliation":[{"name":"Idiap Research Institute,Martigny,Switzerland"}]},{"given":"Andres","family":"Carofilis","sequence":"additional","affiliation":[{"name":"Idiap Research Institute,Martigny,Switzerland"}]},{"given":"Jeena","family":"Prakash","sequence":"additional","affiliation":[{"name":"Uniphore Software Systems,India"}]},{"given":"Sergio","family":"Burdisso","sequence":"additional","affiliation":[{"name":"Idiap Research Institute,Martigny,Switzerland"}]},{"given":"Shashi","family":"Kumar","sequence":"additional","affiliation":[{"name":"Idiap Research Institute,Martigny,Switzerland"}]},{"given":"Esa\u00fa","family":"Villatoro-Tello","sequence":"additional","affiliation":[{"name":"Idiap Research Institute,Martigny,Switzerland"}]},{"given":"Iuliia","family":"Nigmatulina","sequence":"additional","affiliation":[{"name":"Idiap Research Institute,Martigny,Switzerland"}]},{"given":"Petr","family":"Motlicek","sequence":"additional","affiliation":[{"name":"Idiap Research Institute,Martigny,Switzerland"}]},{"given":"Karthik","family":"Pandia","sequence":"additional","affiliation":[{"name":"Uniphore Software Systems,India"}]},{"given":"Aravind","family":"Ganapathiraju","sequence":"additional","affiliation":[{"name":"Uniphore Software Systems,India"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-16438-y"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1142\/s0218001493000455"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3210-1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288848"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707752"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1611"},{"key":"ref9","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2023"},{"key":"ref10","article-title":"MSLAM: Massively multilingual joint pre-training for speech and text","author":"Bapna","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1446"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2122"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.59490\/ejtir.2024.24.4.7531"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746377"},{"key":"ref16","article-title":"Zipformer: A faster and better encoder for automatic speech recognition","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yao"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022724"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178830"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854014"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054309"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746832"},{"key":"ref22","article-title":"Continuous pseudo-labeling from the start","volume-title":"The Eleventh International Conference on Learning Representations","author":"Berrebbi"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3306709"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413869"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446931"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-78"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-105"},{"key":"ref28","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.11591\/eei.v10i5.3157"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658996"},{"key":"ref31","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019"},{"key":"ref32","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"},{"key":"ref33","article-title":"Zipformer: A faster and better encoder for automatic speech recognition","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yao"},{"key":"ref34","article-title":"Lhotse: a speech data representation library for the modern deep learning ecosystem","author":"\u017belasko","year":"2021"},{"key":"ref35","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10340"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref39","first-page":"82","article-title":"Active learning approach for fine-tuning pre-trained asr model for a low-resourced language: A case study of nepali","volume-title":"Proceedings of the 20th International Conference on Natural Language Processing (ICON)","author":"Raj"}],"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\/10888138.pdf?arnumber=10888138","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:41Z","timestamp":1774416281000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888138\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888138","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}