{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:07:25Z","timestamp":1725685645407},"reference-count":13,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T00:00:00Z","timestamp":1695168000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T00:00:00Z","timestamp":1695168000000},"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":[[2023,9,20]]},"DOI":"10.23919\/spa59660.2023.10274438","type":"proceedings-article","created":{"date-parts":[[2023,10,10]],"date-time":"2023-10-10T18:52:57Z","timestamp":1696963977000},"page":"14-18","source":"Crossref","is-referenced-by-count":0,"title":["Augmented Transformer for Speech Detection in Adverse Acoustical Conditions"],"prefix":"10.23919","author":[{"given":"Lukasz","family":"Smietanka","sequence":"first","affiliation":[{"name":"West Pomeranian University of Technology, Szczecin,Faculty of Computer Science and Information Technology,Szczecin,Poland"}]},{"given":"Tomasz","family":"Maka","sequence":"additional","affiliation":[{"name":"West Pomeranian University of Technology, Szczecin,Faculty of Computer Science and Information Technology,Szczecin,Poland"}]}],"member":"263","reference":[{"key":"ref13","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Advances in Neural IInformation Processing Systems"},{"article-title":"Torchaudio: Building blocks for audio and speech processing","year":"2021","author":"yang","key":"ref12"},{"article-title":"A comparison of transformer, convolutional, and recurrent neural networks on phoneme recognition","year":"2022","author":"kyuhong shim","key":"ref11"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"0","author":"dosovitskiy","key":"ref10"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.06.005"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8902703"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-260"},{"article-title":"CNN self-attention voice activity detector","year":"2022","author":"sofer","key":"ref7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414470"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1776"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414445"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472772"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2909472"}],"event":{"name":"2023 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","start":{"date-parts":[[2023,9,20]]},"location":"Poznan, Poland","end":{"date-parts":[[2023,9,22]]}},"container-title":["2023 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10274003\/10274005\/10274438.pdf?arnumber=10274438","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,30]],"date-time":"2023-10-30T18:42:24Z","timestamp":1698691344000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10274438\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,20]]},"references-count":13,"URL":"https:\/\/doi.org\/10.23919\/spa59660.2023.10274438","relation":{},"subject":[],"published":{"date-parts":[[2023,9,20]]}}}