{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T03:49:29Z","timestamp":1768448969025,"version":"3.49.0"},"reference-count":44,"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\/icassp49357.2023.10096988","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":24,"title":["Wav2Seq: Pre-Training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages"],"prefix":"10.1109","author":[{"given":"Felix","family":"Wu","sequence":"first","affiliation":[{"name":"ASAPP Inc."}]},{"given":"Kwangyoun","family":"Kim","sequence":"additional","affiliation":[{"name":"ASAPP Inc."}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Kyu J.","family":"Han","sequence":"additional","affiliation":[{"name":"ASAPP Inc."}]},{"given":"Ryan","family":"McDonald","sequence":"additional","affiliation":[{"name":"ASAPP Inc."}]},{"given":"Kilian Q.","family":"Weinberger","sequence":"additional","affiliation":[{"name":"ASAPP Inc."}]},{"given":"Yoav","family":"Artzi","sequence":"additional","affiliation":[{"name":"ASAPP Inc."}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747432"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2059"},{"key":"ref34","article-title":"Scikit-learn: Machine learning in Python","author":"pedregosa","year":"2011","journal-title":"JMLR"},{"key":"ref15","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"ICML"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2025"},{"key":"ref14","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","author":"baevski","year":"2022","journal-title":"ICML"},{"key":"ref36","article-title":"Tying word vectors and word classifiers: A loss framework for language modeling","author":"inan","year":"2017","journal-title":"ICLRE"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683535"},{"key":"ref33","article-title":"K-means++: The advantages of careful seeding","author":"arthur","year":"2007","journal-title":"SODA"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772862"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref1","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018"},{"key":"ref17","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"NIPS"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2482"},{"key":"ref16","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"NeurIPS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639513"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1912"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref24","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"raffel","year":"2019","journal-title":"JMLR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref26","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref25","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2020","journal-title":"ICLRE"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-143"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10368"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00343"},{"key":"ref21","article-title":"Wav2seq: Pre-training speech-to-text encoder-decoder models using pseudo languages","author":"wu","year":"2022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.68"},{"key":"ref28","article-title":"Generative spoken language modeling from raw audio","author":"lakhotia","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.393"},{"key":"ref29","article-title":"A new algorithm for data compression","author":"gage","year":"1994","journal-title":"C Users Journal"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746137"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref9","article-title":"Wav2letter: an end-to-end convnet-based speech recognition system","author":"collobert","year":"2016"},{"key":"ref4","article-title":"HuBERT: How much can a bad teacher benefit asr pre-training","author":"hsu","year":"2020","journal-title":"NeurIPS SAS"},{"key":"ref3","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref6","article-title":"Covost 2 and massively multilingual speech-to-text translation","author":"wang","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.53"}],"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\/10096988.pdf?arnumber=10096988","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:04:26Z","timestamp":1700507066000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096988\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096988","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}