{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T16:22:20Z","timestamp":1768407740109,"version":"3.49.0"},"reference-count":20,"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\/spa59660.2023.10274442","type":"proceedings-article","created":{"date-parts":[[2023,10,10]],"date-time":"2023-10-10T18:52:57Z","timestamp":1696963977000},"page":"19-24","source":"Crossref","is-referenced-by-count":9,"title":["A survey of automatic speech recognition deep models performance for Polish medical terms"],"prefix":"10.23919","author":[{"given":"Marta","family":"Zielonka","sequence":"first","affiliation":[{"name":"University of Technology,Faculty of Electronics, Telecommunications and Informatics at Gdańsk,Multimedia Systems Department"}]},{"given":"Wiktor","family":"Krasi\u0144ski","sequence":"additional","affiliation":[{"name":"University of Technology,Faculty of Electronics, Telecommunications and Informatics at Gdańsk,Multimedia Systems Department"}]},{"given":"Jakub","family":"Nowak","sequence":"additional","affiliation":[{"name":"University of Technology,Faculty of Electronics, Telecommunications and Informatics at Gdańsk,Multimedia Systems Department"}]},{"given":"Przemys\u0142aw","family":"Ro\u015ble\u0144","sequence":"additional","affiliation":[{"name":"University of Technology,Faculty of Electronics, Telecommunications and Informatics at Gdańsk,Multimedia Systems Department"}]},{"given":"Jan","family":"Stopi\u0144ski","sequence":"additional","affiliation":[{"name":"University of Technology,Faculty of Electronics, Telecommunications and Informatics at Gdańsk,Multimedia Systems Department"}]},{"given":"Mateusz","family":"\u017bak","sequence":"additional","affiliation":[{"name":"University of Technology,Faculty of Electronics, Telecommunications and Informatics at Gdańsk,Multimedia Systems Department"}]},{"given":"Franciszek","family":"G\u00f3rski","sequence":"additional","affiliation":[{"name":"University of Technology,Faculty of Electronics, Telecommunications and Informatics at Gdańsk,Multimedia Systems Department"}]},{"given":"Andrzej","family":"Czy\u017cewski","sequence":"additional","affiliation":[{"name":"University of Technology,Faculty of Electronics, Telecommunications and Informatics at Gdańsk,Multimedia Systems Department"}]}],"member":"263","reference":[{"key":"ref13","year":"0","journal-title":"Voice synthetiser speechgen io"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682890"},{"key":"ref15","year":"0","journal-title":"OpenAI Whisper latest release official github"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2004-668"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747760"},{"key":"ref11","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"casper","year":"0"},{"key":"ref10","article-title":"Conformer: Convolution-augmented transformer for speech recognition","author":"chiu","year":"0"},{"key":"ref2","year":"0","journal-title":"Package Documentation"},{"key":"ref1","year":"0","journal-title":"Distance package documentation"},{"key":"ref17","year":"0","journal-title":"Audacity documentation"},{"key":"ref16","article-title":"Robust speech recognition via large-scale weak supervision","author":"tao","year":"0"},{"key":"ref19","author":"parmar","year":"0","journal-title":"Attention is all you need"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/INDICON56171.2022.10039985"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747637"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687910"},{"key":"ref9","year":"0","journal-title":"Google Google stt documentation"},{"key":"ref4","year":"0","journal-title":"Speech to text – audio to text translation | microsoft azure"},{"key":"ref3","year":"0","journal-title":"Speech-to-Text Automatic Speech Recognition | Google Cloud"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054450"},{"key":"ref5","author":"graves","year":"0","journal-title":"Sequence transduction with recurrent neural networks"}],"event":{"name":"2023 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","location":"Poznan, Poland","start":{"date-parts":[[2023,9,20]]},"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\/10274442.pdf?arnumber=10274442","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T18:57:17Z","timestamp":1699297037000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10274442\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,20]]},"references-count":20,"URL":"https:\/\/doi.org\/10.23919\/spa59660.2023.10274442","relation":{},"subject":[],"published":{"date-parts":[[2023,9,20]]}}}