{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:06:29Z","timestamp":1775199989798,"version":"3.50.1"},"reference-count":59,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434713","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["SincQDR-VAD: A Noise-Robust Voice Activity Detection Framework Leveraging Learnable Filters and Ranking-Aware Optimization"],"prefix":"10.1109","author":[{"given":"Chien-Chun","family":"Wang","sequence":"first","affiliation":[{"name":"National Taiwan Normal University,Dept. Computer Science and Information Engineering,Taiwan"}]},{"given":"En-Lun","family":"Yu","sequence":"additional","affiliation":[{"name":"National Taiwan Normal University,Dept. Computer Science and Information Engineering,Taiwan"}]},{"given":"Jeih-Weih","family":"Hung","sequence":"additional","affiliation":[{"name":"National Chi Nan University,Taiwan"}]},{"given":"Shih-Chieh","family":"Huang","sequence":"additional","affiliation":[{"name":"Realtek Semiconductor Corp.,Taiwan"}]},{"given":"Berlin","family":"Chen","sequence":"additional","affiliation":[{"name":"National Taiwan Normal University,Dept. Computer Science and Information Engineering,Taiwan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078610"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639096"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2229986"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/97.736233"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637694"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707749"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2909472"},{"key":"ref8","article-title":"Voice activity detection in presence of background noise using EEG","author":"Krishna","year":"2019","journal-title":"Arxiv preprint arXiv:1911.04261"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054761"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-0995"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053412"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2285"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054358"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3073596"},{"key":"ref15","article-title":"Improvement of noise-robust single-channel voice activity detection with spatial pre-processing","volume-title":"Proc. Interspeech","author":"V\u00e6hrens"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1977"},{"key":"ref17","article-title":"Cross-domain voice activity detection with self-supervised representations","author":"Alisamir","year":"2022","journal-title":"Arxiv preprint arXiv:2209.11061"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10033"},{"key":"ref19","article-title":"BC-VAD: A robust bone conduction voice activity detection","author":"Polvani","year":"2022","journal-title":"Arxiv preprint arXiv:2212.02996"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10535"},{"key":"ref21","article-title":"CNN self-attention voice activity detector","author":"Sofer","year":"2022","journal-title":"Arxiv preprint arXiv:2203.02944"},{"key":"ref22","article-title":"Voice activity detection (VAD) in noisy environments","author":"Ball","year":"2023","journal-title":"Arxiv preprint arXiv:2312.05815"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-598"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-716"},{"key":"ref25","article-title":"CLIP-VAD: Exploiting vision-language models for voice activity detection","author":"Appiani","year":"2024","journal-title":"Arxiv preprint arXiv:2410.14509"},{"key":"ref26","article-title":"A real-time voice activity detection based on lightweight neural","author":"Jia","year":"2024","journal-title":"Arxiv preprint arXiv:2405.16797"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-1019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-2489"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3369531"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446945"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682532"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414470"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096938"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-820"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446312"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5724-z"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462015"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10445878"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-365"},{"key":"ref41","article-title":"Benchmarking deep AUROC optimization: Loss functions and algorithmic choices","author":"Zhu","year":"2022","journal-title":"Arxiv preprint arXiv:2203.14177"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-022-00260-9"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2028"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2811740"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1981.1163506"},{"key":"ref46","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017","journal-title":"Arxiv preprint arXiv:1708.04552"},{"key":"ref47","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018","journal-title":"Arxiv preprint arXiv:1803.01271"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"ref49","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018","journal-title":"Arxiv preprint arXiv:1804.03209"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502245"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref52","article-title":"An overview of gradient descent optimization algorithms","author":"Ruder","year":"2016","journal-title":"Arxiv preprint arXiv:1609.04747"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00065"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/S0031-3203(96)00142-2"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415081"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746755"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-975"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616082"},{"key":"ref59","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"Arxiv preprint arXiv:2312.00752"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434713.pdf?arnumber=11434713","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:58:39Z","timestamp":1775192319000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434713\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434713","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}