{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T09:46:15Z","timestamp":1726047975178},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095888","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Multilingual Word Error Rate Estimation: E-Wer3"],"prefix":"10.1109","author":[{"given":"Shammur Absar","family":"Chowdhury","sequence":"first","affiliation":[{"name":"HBKU,Qatar Computing Research Institute,Doha,Qatar"}]},{"given":"Ahmed","family":"Ali","sequence":"additional","affiliation":[{"name":"HBKU,Qatar Computing Research Institute,Doha,Qatar"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2396761.2398730"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846279"},{"key":"ref15","article-title":"Simple and effective zero-shot cross-lingual phoneme recognition","author":"xu","year":"2021","journal-title":"arXiv preprint arXiv 2109 11399"},{"key":"ref14","article-title":"Unsupervised cross-lingual representation learning for speech recognition","author":"conneau","year":"2020","journal-title":"arXiv preprint arXiv 2006 13823"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1881"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.177"},{"key":"ref10","article-title":"Common voice: A massively-multilingual speech corpus","author":"ardila","year":"2019","journal-title":"arXiv preprint arXiv 1912 06670"},{"key":"ref2","article-title":"English conversational telephone speech recognition by humans and machines","author":"saon","year":"2017","journal-title":"arXiv preprint arXiv 1703 01362"},{"key":"ref1","article-title":"Achieving human parity in conversational speech recognition","author":"xiong","year":"2016","journal-title":"arXiv preprint arXiv 1610 05256"},{"key":"ref17","article-title":"Unsupervised cross-lingual representation learning at scale","author":"conneau","year":"2019","journal-title":"arXiv preprint arXiv 1911 11698"},{"key":"ref16","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv preprint arXiv 1810 04805"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1809"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref8","article-title":"Neural zero-inflated quality estimation model for automatic speech recognition system","author":"fan","year":"2019","journal-title":"arXiv preprint arXiv 1910 01500"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2357"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683086"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2854946.2854961"},{"key":"ref3","first-page":"1813","article-title":"Quality estimation for automatic speech recognition","author":"negri","year":"2014","journal-title":"Proceedings of COLING 2014 the 25th International Conference on Computational Linguistics Technical Papers"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2004"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-4008"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095888.pdf?arnumber=10095888","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T18:58:55Z","timestamp":1699901935000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095888\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095888","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}