{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T06:40:13Z","timestamp":1741243213078,"version":"3.38.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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":[[2024,12,1]]},"DOI":"10.1109\/tencon61640.2024.10902805","type":"proceedings-article","created":{"date-parts":[[2025,3,5]],"date-time":"2025-03-05T18:40:14Z","timestamp":1741200014000},"page":"1194-1197","source":"Crossref","is-referenced-by-count":0,"title":["Significance of Corpus Quality for Direct Speech-to-Text Translation Systems"],"prefix":"10.1109","author":[{"given":"Tonmoy","family":"Rajkhowa","sequence":"first","affiliation":[{"name":"Indian Institute of Technology (BHU),Dept. of Electronics Engineering,Varanasi,India"}]},{"given":"Amartya Roy","family":"Chowdhury","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology,Dept. of EECE,Dharwad,India"}]},{"given":"Lokesh","family":"Kumar","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology,Dept. of EECE,Dharwad,India"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2076"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-48309-7_3"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.224"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17508"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.406"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1006"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053847"},{"article-title":"Don\u2019t discard fixed-window audio segmentation in speech-to-text translation","volume-title":"Proceedings of the Seventh Conference on Machine Translation (WMT)","author":"Amrhein","key":"ref8"},{"key":"ref9","article-title":"Revisiting end-to-end speech-to-text translation from scratch","volume-title":"International Conference on Machine Learning","author":"Zhang","year":"2022"},{"article-title":"Improved speech-to-text translation with the fisher and callhome Spanish-English speech translation corpus","volume-title":"Proceedings of the 10th International Workshop on Spoken Language Translation: Papers","author":"Post","key":"ref10"},{"article-title":"MuST -C: a Multilingual Speech Translation Corpus","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Di Gangi","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-11"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054626"},{"key":"ref14","article-title":"Librivoxdeen: A cor-pus for german-to-english speech translation and speech recognition","volume-title":"Proceedings of the Language Resources and Evaluation Conference","author":"Beilharz","year":"2020"},{"journal-title":"Covost 2: A massively multilingual speech-to-text translation corpus","year":"2020","author":"Wang","key":"ref15"},{"article-title":"CoVoST: A diverse multilin-gual speech-to-text translation corpus","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference","author":"Wang","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.2481\/dsj.6.S806"},{"article-title":"Prab-hupadavani: A code-mixed speech translation data for 25 languages","volume-title":"Proceedings of the 6th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature","author":"Sandhan","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref20","article-title":"Seamlessm4t-massively multilingual & multimodal machine translation","author":"Barrault","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00452"},{"journal-title":"Vakyansh: Asr toolkit for low resource indic languages","year":"2022","author":"Chadha","key":"ref22"},{"journal-title":"Clsril-23: Cross lingual speech representations for indic languages","year":"2021","author":"Gupta","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"}],"event":{"name":"TENCON 2024 - 2024 IEEE Region 10 Conference (TENCON)","start":{"date-parts":[[2024,12,1]]},"location":"Singapore, Singapore","end":{"date-parts":[[2024,12,4]]}},"container-title":["TENCON 2024 - 2024 IEEE Region 10 Conference (TENCON)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10902665\/10902666\/10902805.pdf?arnumber=10902805","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T06:06:14Z","timestamp":1741241174000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10902805\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,1]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/tencon61640.2024.10902805","relation":{},"subject":[],"published":{"date-parts":[[2024,12,1]]}}}