{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:11:24Z","timestamp":1775067084152,"version":"3.50.1"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T00:00:00Z","timestamp":1701648000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T00:00:00Z","timestamp":1701648000000},"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":[[2023,12,4]]},"DOI":"10.1109\/o-cocosda60357.2023.10482960","type":"proceedings-article","created":{"date-parts":[[2024,4,2]],"date-time":"2024-04-02T18:38:10Z","timestamp":1712083090000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Optimizing Direct Speech-to-Text Translation for un-orthographic low-resource tribal languages using source transliterations"],"prefix":"10.1109","author":[{"given":"Tonmoy","family":"Rajkhowa","sequence":"first","affiliation":[{"name":"IIT Dharwad,Dept. of Electrical Engineering,Dharwad,India"}]},{"given":"Amartya","family":"Roy Chowdhury","sequence":"additional","affiliation":[{"name":"IIT Dharwad,Dept. of Electrical Engineering,Dharwad,India"}]},{"given":"Prashant","family":"Bannulmath","sequence":"additional","affiliation":[{"name":"IIIT Dharwad,Dept. of Electronics and Communication,Dharwad,India"}]},{"given":"Deepak","family":"K.T.","sequence":"additional","affiliation":[{"name":"IIIT Dharwad,Dept. of Electronics and Communication,Dharwad,India"}]},{"given":"S. R. Mahadeva","family":"Prasanna","sequence":"additional","affiliation":[{"name":"IIT Dharwad,Dept. of Electrical Engineering,Dharwad,India"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Listen and translate: A proof of concept for end-to-end speech-to-text translation","author":"B\u00e9rard","year":"2016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1109"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1133"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-503"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461690"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2008.918415"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683343"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.iwslt-1.29"},{"key":"ref9","article-title":"Data efficient direct speech-to-text translation with modality agnostic meta-learning","author":"Indurthi","year":"2019"},{"key":"ref10","first-page":"55","article-title":"Beyond voice activity detection: Hybrid audio segmentation for direct speech translation","volume-title":"Proceedings of the 4th International Conference on Natural Language and Speech Processing (ICNLSP 2021)","author":"Gaido"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.485"},{"key":"ref12","first-page":"2012","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":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-11"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054626"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2006.326795"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404809"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-862"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1263"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-0123"},{"key":"ref20","article-title":"Languages of Tamil Nadu: Lambadi, an Indo-Aryan dialect","volume":"ix","author":"Boopathy","year":"1972","journal-title":"Census of India 1961, Tamil Nadu"},{"key":"ref21","volume-title":"Ethnography of a denotified tribe: the Laman Banjara.","author":"Burman","year":"2010"},{"key":"ref22","author":"Trail","year":"1970","journal-title":"The grammar of Lamani. SIL of the Univ. of Oklahoma"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/jhg.2010.173"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/jhg.2011.8"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.4324\/9780203068137-14"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.350"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683550"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1326"},{"key":"ref29","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":"ref30","article-title":"Librivoxdeen: A corpus for german-to-english speech translation and german speech recognition","author":"Beilharz","year":"2019"},{"key":"ref31","first-page":"4197","article-title":"CoVoST: A diverse multilingual speech-to-text translation corpus","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference","author":"Wang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053847"},{"key":"ref33","first-page":"632","article-title":"End-to-end automatic speech recognition with deep mutual learning","volume-title":"2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","author":"Masumura"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-526"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.376"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1017\/s0041977x0009087x"},{"key":"ref37","article-title":"Soliga tribes\u2019culture and identity","author":"Spandana","year":"2023","journal-title":"International Research Journal of Modernization in Engineering Technology and Science"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref42","article-title":"Fairseq s2t: Fast speech-to-text modeling with fairseq","author":"Wang","year":"2020"},{"issue":"10","key":"ref43","first-page":"1995","article-title":"Convolutional networks for images, speech, and time series","volume":"3361","author":"LeCun","year":"1995","journal-title":"The handbook of brain theory and neural networks"},{"key":"ref44","first-page":"12 449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"}],"event":{"name":"2023 26th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","location":"Delhi, India","start":{"date-parts":[[2023,12,4]]},"end":{"date-parts":[[2023,12,6]]}},"container-title":["2023 26th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10482896\/10482911\/10482960.pdf?arnumber=10482960","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,3]],"date-time":"2024-04-03T05:35:53Z","timestamp":1712122553000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10482960\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,4]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/o-cocosda60357.2023.10482960","relation":{},"subject":[],"published":{"date-parts":[[2023,12,4]]}}}