{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:23:10Z","timestamp":1774419790534,"version":"3.50.1"},"reference-count":27,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890761","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Sagalee: an Open Source Automatic Speech Recognition Dataset for Oromo Language"],"prefix":"10.1109","author":[{"given":"Turi","family":"Abu","sequence":"first","affiliation":[{"name":"BNRist,Center for Speech and Language Technologies,Beijing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Shi","sequence":"additional","affiliation":[{"name":"BNRist,Center for Speech and Language Technologies,Beijing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas Fang","family":"Zheng","sequence":"additional","affiliation":[{"name":"BNRist,Center for Speech and Language Technologies,Beijing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Wang","sequence":"additional","affiliation":[{"name":"BNRist,Center for Speech and Language Technologies,Beijing"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102422"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-10073-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref4","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"},{"key":"ref5","article-title":"The development of written afan oromo and the appropriateness of qubee, latin script, for afan oromo writing","volume":"28","author":"Tegegne","year":"2016","journal-title":"Historical Research Letter"},{"key":"ref6","article-title":"Historical challenges in the development of the oromo language and some agenda for future research","volume-title":"The journal of Oromo studies","volume":"3","author":"Demie","year":"1996"},{"issue":"3","key":"ref7","first-page":"550","article-title":"The oromo orthography of shaykh bakri sapalo","volume-title":"Bulletin of the School of Oriental and African Studies, University of London","volume":"44","author":"Hayward","year":"1981"},{"key":"ref8","article-title":"Some aspects of oromo history that have been misunderstood","volume-title":"The journal of Oromo studies","volume":"1","author":"Hassen","year":"1994"},{"key":"ref9","article-title":"Qube afaan oromo: Reasons for choosing the latin script for developing an oromo alphabet","volume-title":"The journal of Oromo studies","volume":"1","author":"Gamta","year":"1993"},{"key":"ref10","volume-title":"A Comparative Study of Three Southern Oromo Dialects in Kenya: Phonology, Morphology and Vocabulary","author":"Stroomer","year":"1987"},{"key":"ref11","volume-title":"A Grammatical Sketch of Written Oromo","author":"Griefenow-Mewis","year":"2001"},{"key":"ref12","first-page":"5071","article-title":"A survey of multilingual models for automatic speech recognition","volume-title":"Proceedings of the Thirteenth Language Resources and Evaluation Conference","author":"Yadav"},{"key":"ref13","article-title":"Stable distillation: Regularizing continued pre-training for low-resource automatic speech recognition","author":"Seth","year":"2023"},{"key":"ref14","article-title":"Knowledge distillation from multiple foundation models for end-to-end speech recognition","author":"Yang","year":"2023"},{"key":"ref15","article-title":"Effectiveness of self-supervised pre-training for speech recognition","author":"Baevski","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2680"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054130"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1679"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854673"},{"key":"ref20","article-title":"Crowdsourcing parallel corpus for english-oromo neural machine translation using community engagement platform","author":"Chala","year":"2021"},{"key":"ref21","article-title":"Afan oromo speech-based computer command and control: An evaluation with selected commands","volume":"2023","author":"Kebede","year":"2023","journal-title":"Jimma Institute of Technology Electrical and Computer Engineering"},{"key":"ref22","first-page":"13","article-title":"Large vocabulary read speech corpora for four Ethiopian languages: Amharic, Tigrigna, Oromo, and Wolaytta","volume-title":"Proceedings of the Fourth Widening Natural Language Processing Workshop","author":"Abate"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"ref24","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref25","article-title":"Swish: a self-gated activation function","author":"Ramachandran","year":"2017"},{"key":"ref26","first-page":"1715","article-title":"Neural machine translation of rare words with subword units","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Sennrich"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10835"}],"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\/10890761.pdf?arnumber=10890761","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:42Z","timestamp":1774416282000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890761\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890761","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}