{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:15:39Z","timestamp":1740100539515,"version":"3.37.3"},"reference-count":59,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["ACI-1548562"],"award-info":[{"award-number":["ACI-1548562"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688276","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"1050-1057","source":"Crossref","is-referenced-by-count":0,"title":["Cross-Lingual Transfer for Speech Processing Using Acoustic Language Similarity"],"prefix":"10.1109","author":[{"given":"Peter","family":"Wu","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,PA,USA"}]},{"given":"Jiatong","family":"Shi","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,PA,USA"}]},{"given":"Yifan","family":"Zhong","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,PA,USA"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,PA,USA"}]},{"given":"Alan W","family":"Black","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,PA,USA"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.sigtyp-1.11"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2278"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1977.1170198"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367298"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref30","first-page":"322","article-title":"Voice building from insufficient data-classroom experiences with web-based language development tools","author":"kominek","year":"0","journal-title":"SSW"},{"key":"ref37","article-title":"A python toolkit for universal transliteration","author":"qian","year":"2010","journal-title":"LREC"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref35","article-title":"Supervised contrastive learning","author":"khosla","year":"2020","journal-title":"NeurIPS"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"Voxceleb: A large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"InterSpeech"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-488"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-15"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-306"},{"key":"ref2","article-title":"Submission from CMU for blizzard challenge 2019","volume":"2019","author":"rallabandi","year":"0","journal-title":"Proceedings of Blizzard Challenge"},{"key":"ref1","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"0","journal-title":"InterSpeech"},{"journal-title":"The World Atlas of Language Structures Online","year":"2013","author":"dryer","key":"ref20"},{"journal-title":"PHOIBLE 2 0","year":"2019","author":"moran","key":"ref22"},{"key":"ref21","article-title":"Automatically identifying language family from acoustic examples in low resource scenarios","author":"wu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683536"},{"journal-title":"Syntactic structures of the world's languages (SSWL)","year":"2009","author":"collins","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-328"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s00190-012-0578-z"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-31"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/2792745.2792775"},{"key":"ref58","volume":"128","author":"towns","year":"2014","journal-title":"Xsede Accelerating scientific discovery computing in science & engineering 16 (5) 62–74 sep 2014"},{"key":"ref57","article-title":"Multibench: Multiscale benchmarks for multi-modal representation learning","author":"liang","year":"2021","journal-title":"NeurIPS"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475247"},{"key":"ref55","article-title":"Task-specific pre-training and cross lingual transfer for sentiment analysis in Dravidian code-switched languages","author":"gupta","year":"0","journal-title":"Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages"},{"key":"ref54","article-title":"Towards client-side privacy for downstream speech tasks","author":"wu","year":"0","journal-title":"APSIPA"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2955"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953167"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461972"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2831"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6256"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268945"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6341"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2002"},{"journal-title":"Ethnologue Languages of the World","year":"2020","key":"ref18"},{"journal-title":"Glottolog 4 3","year":"2020","author":"hammarstr\u00f6m","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2164"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461802"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3052"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1009"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1299"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref9","article-title":"Choosing transfer languages for crosslingual learning","author":"lin","year":"0","journal-title":"ACL"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref45","article-title":"Common voice: A massively-multilingual speech corpus","author":"ardila","year":"2020","journal-title":"LREC"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref42","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-318"},{"key":"ref43","first-page":"52","article-title":"Crowd-sourced speech corpora for javanese, sundanese, sinhala, nepali, and bangladeshi bengali","author":"kjartansson","year":"0","journal-title":"Proc The 6th Intl Workshop on Spoken Language Technologies for Under-Resourced Languages"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2021,12,13]]},"location":"Cartagena, Colombia","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688276.pdf?arnumber=9688276","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:41:23Z","timestamp":1652733683000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688276\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688276","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}