{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T10:13:20Z","timestamp":1758190400669,"version":"3.44.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T00:00:00Z","timestamp":1754179200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T00:00:00Z","timestamp":1754179200000},"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":[[2025,8,3]]},"DOI":"10.1109\/ialp68296.2024.11156289","type":"proceedings-article","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T17:32:18Z","timestamp":1758043938000},"page":"266-271","source":"Crossref","is-referenced-by-count":0,"title":["Robust Speech Recognition for Visual Acuity Testing in Multi-Speaker Clinical Environments"],"prefix":"10.1109","author":[{"given":"Akshita","family":"Abrol","sequence":"first","affiliation":[{"name":"Singapore Institute of Technology,Infocomm Technology,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ridwan","family":"Arefeen","sequence":"additional","affiliation":[{"name":"Singapore Institute of Technology,Infocomm Technology,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kelvin Zhenghao","family":"Li","sequence":"additional","affiliation":[{"name":"Tan Tock Seng Hospital,Department of Ophthalmology,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengkui","family":"Wang","sequence":"additional","affiliation":[{"name":"Singapore Institute of Technology,Infocomm Technology,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rong","family":"Tong","sequence":"additional","affiliation":[{"name":"Singapore Institute of Technology,Infocomm Technology,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1167\/tvst.8.4.27"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1136\/bmjophth-2021-000801"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1097\/OPX.0000000000001551"},{"issue":"11","key":"ref4","article-title":"Validation of the smartphonebased snellen visual acuity chart for vision screening","author":"Gupta","year":"2023","journal-title":"Optometry & Visual Performance"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2022.020376"},{"key":"ref6","article-title":"Libri2vox dataset: Target speaker extraction with diverse speaker conditions and synthetic data","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/ICASSP39728.2021.9413901","article-title":"Attention is all you need in speech separation","volume-title":"ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Subakan","year":"2021"},{"key":"ref8","article-title":"Speech enabled visual acuity test","volume-title":"Proceedings of Interspeech 2024","author":"Yap","year":"2024"},{"key":"ref9","article-title":"Evaluating the performance of using speaker diarization for speech separation of in-person role-play dialogues","author":"Medaramitta","year":"2021","journal-title":"arXiv"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2018.8462116"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1893"},{"issue":"4","key":"ref13","doi-asserted-by":"crossref","first-page":"331","DOI":"10.25046\/aj050439","article-title":"Distributed microphone arrays, emerging speech and audio signal processing platforms: A review","volume":"5","author":"Pasha","year":"2020","journal-title":"Advances in Science, Technology and Engineering Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2024.104408"},{"issue":"3","key":"ref15","first-page":"456","article-title":"Speech enhancement for cochlear implant recipients using deep complex convolution transformer with frequency transformation","volume":"32","author":"Mamun","year":"2024","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ICASSP43922.2022.9747375","article-title":"Extended graph temporal classification for multi-speaker end-to-end asr","volume-title":"ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Chang","year":"2022"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"10356","DOI":"10.1109\/ICASSP48485.2024.10445985","article-title":"Mossformer2: Combining transformer and rnn-free recurrent network for enhanced time-domain monaural speech separation","volume-title":"ICASSP 2024\u20132024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Zhao","year":"2024"},{"volume-title":"Whisper: Robust speech recognition via large-scale weak supervision","year":"2022","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"volume-title":"Faster-whisper: Faster and memory-efficient whisper inference","year":"2023","key":"ref21"},{"issue":"2","key":"ref22","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref23","article-title":"Librimix: An open-source dataset for generalizable speech separation","author":"Cosentino","year":"2020","journal-title":"arXiv preprint arXiv"}],"event":{"name":"2025 International Conference on Asian Language Processing (IALP)","start":{"date-parts":[[2025,8,3]]},"location":"Sarawak, Malaysia","end":{"date-parts":[[2025,8,6]]}},"container-title":["2025 International Conference on Asian Language Processing (IALP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11156192\/11156242\/11156289.pdf?arnumber=11156289","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T05:10:59Z","timestamp":1758085859000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11156289\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/ialp68296.2024.11156289","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]}}}