{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T09:31:43Z","timestamp":1770975103802,"version":"3.50.1"},"reference-count":38,"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\/icassp49357.2023.10096977","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":7,"title":["Euro: Espnet Unsupervised ASR Open-Source Toolkit"],"prefix":"10.1109","author":[{"given":"Dongji","family":"Gao","sequence":"first","affiliation":[{"name":"Johns Hopkins University"}]},{"given":"Jiatong","family":"Shi","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Shun-Po","family":"Chuang","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]},{"given":"Leibny Paola","family":"Garcia","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Sanjeev","family":"Khudanpur","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}]}],"member":"263","reference":[{"key":"ref13","article-title":"MLS: A large-scale multi-lingual dataset for speech research","author":"pratap","year":"2020","journal-title":"InterSpeech"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref12","article-title":"Timit acoustic-phonetic continuous speech corpus ldc93s1","author":"garofolo","year":"1993","journal-title":"Linguistic Data Consortium"},{"key":"ref34","article-title":"Libri-light: A bench-mark for asr with limited or no supervision","author":"kahn","year":"2020","journal-title":"ICASSP"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref37","author":"lee","year":"2018","journal-title":"Learning pronunciation from a foreign language in speech synthesis networks"},{"key":"ref14","article-title":"Developments of Swahili resources for an automatic speech recognition system","author":"gelas","year":"2012","journal-title":"SLTU"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414714"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461974"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref33","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref10","article-title":"Unsupervised speech recognition","author":"baevski","year":"2021","journal-title":"NeurIPS"},{"key":"ref32","article-title":"Unsupervised speech recognition via segmental empirical output distribution matching","author":"yeh","year":"2019","journal-title":"ICLRE"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2059"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1800"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2792745.2792775"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref18","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"ASRU"},{"key":"ref24","article-title":"Flashlight: Enabling innovation in tools for machine learning","author":"kahn","year":"2022","journal-title":"ICML"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref26","article-title":"Improved training of wasserstein GANs","author":"gulrajani","year":"2017","journal-title":"NeurIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462463"},{"key":"ref20","author":"kuang","year":"2020","journal-title":"K2"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0184"},{"key":"ref21","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"NeurIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref27","author":"g","year":"2008","journal-title":"Supervised Sequence Labelling with Recurrent Neural Networks"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288848"},{"key":"ref8","article-title":"Towards the automatic processing of Yongning Na (Sino-Tibetan): developing a light acoustic model of the target language and testing heavyweight models from five national languages","author":"michaud","year":"2014","journal-title":"SLTU"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref9","article-title":"Leveraging end-to-end asr for endangered language documentation: An empirical study on yoloxochitl mixtec","author":"shi","year":"2020","journal-title":"EACL"},{"key":"ref4","author":"grenoble","year":"2011","journal-title":"Handbook of endan-gered languages"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref5","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"NeurIPS"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"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\/10096977.pdf?arnumber=10096977","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:06:13Z","timestamp":1700507173000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096977\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096977","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}