{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T05:41:03Z","timestamp":1764222063099,"version":"3.46.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/sped67700.2025.11252407","type":"proceedings-article","created":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T19:00:27Z","timestamp":1764183627000},"page":"108-113","source":"Crossref","is-referenced-by-count":0,"title":["Cross-lingual Transfer Learning Experiments for Arabic ASR"],"prefix":"10.1109","author":[{"given":"Amin","family":"Hassairi","sequence":"first","affiliation":[{"name":"Budapest University of Technology and Economics,Dept. of Telecommunications and Artificial Intelligence,Budapest,Hungary"}]},{"given":"P\u00e9ter","family":"Mihajlik","sequence":"additional","affiliation":[{"name":"Budapest University of Technology and Economics,Dept. of Telecommunications and Artificial Intelligence,Budapest,Hungary"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.07.008"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3184480"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2620"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/PRML56267.2022.9882228"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SpeD59241.2023.10314867"},{"key":"ref9","first-page":"6381","article-title":"Streaming end-to-end speech recognition for mobile devices","volume-title":"Proc. ICASSP","author":"Y. H"},{"key":"ref10","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume-title":"Proceedings of the 31st International Conference on Machine Learning (ICML)","author":"Graves"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"article-title":"Sequence transduction with recurrent neural networks","volume-title":"ICML Workshop on Representation Learning","author":"Graves","key":"ref13"},{"article-title":"Conformer: Convolution-augmented transformer for speech recognition","volume-title":"arXiv preprint arXiv:2005.08100","author":"A. G","key":"ref14"},{"key":"ref15","article-title":"Recent developments on end-to-end automatic speech recognition","author":"Guo","year":"2021","journal-title":"arXiv preprint arXiv:2105.11151"},{"key":"ref16","first-page":"1","article-title":"Transformer transducer: One model unifying streaming and non-streaming speech recognition","volume-title":"Proc. of INTERSPEECH","author":"Zhang"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424246"},{"volume-title":"A transfer learning approach for under-resourced arabic dialects speech recognition","year":"2012","author":"Elmahdy","key":"ref18"},{"key":"ref19","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"arXiv preprint arXiv:2006.11477"},{"key":"ref20","article-title":"Xls-r: Self-supervised cross-lingual speech representation learning at scale","author":"A. B","year":"2021","journal-title":"arXiv preprint arXiv:2111.09296"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref22","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023","journal-title":"arXiv preprint arXiv:2212.04356"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846279"},{"key":"ref24","first-page":"214 582","article-title":"A survey on arabic speech recognition systems","volume":"8","author":"Khalifa","year":"2020","journal-title":"IEEE Access"},{"issue":"5","key":"ref25","first-page":"343","article-title":"Arabic end-to-end speech recognition using encoder-decoder models","volume":"17","author":"Ibrahim","year":"2023","journal-title":"IET Signal Processing"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101272"},{"volume-title":"Mozilla common voice project","year":"2025","key":"ref27"},{"key":"ref28","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2019","journal-title":"arXiv preprint arXiv:1912.06670"},{"journal-title":"arXiv preprint arXiv:2412.13788","article-title":"Open universal arabic asr leaderboard","year":"2024","key":"ref29"},{"key":"ref30","article-title":"N-shot benchmarking of whisper on diverse arabic speech recognition","author":"Talafha","year":"2023","journal-title":"arXiv preprint arXiv:2306.02902"},{"journal-title":"arXiv preprint arXiv:2310.11069, Oct. 2023, authors\u2019 affiliations: \u03beDeep Learning & NLP Group, The University of British Columbia; \u03bbDepartment of NLP & Machine Learning, MBZUAI","article-title":"A robust dialect-aware arabic speech recognition system","author":"Waheed","key":"ref31"},{"key":"ref32","article-title":"Casablanca: Data and models for multidialectal arabic speech recognition","author":"Talafha","year":"2024","journal-title":"arXiv preprint arXiv:2410.04527"},{"article-title":"Experiment tracking with weights and biases","volume-title":"Proc. 2020 Conf. on Machine Learning Tools, Weights & Biases","author":"Biewald","key":"ref33"}],"event":{"name":"2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","start":{"date-parts":[[2025,10,19]]},"location":"Cluj-Napoca, Romania","end":{"date-parts":[[2025,10,22]]}},"container-title":["2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11251505\/11251597\/11252407.pdf?arnumber=11252407","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T05:37:40Z","timestamp":1764221860000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11252407\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/sped67700.2025.11252407","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}