{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:34:13Z","timestamp":1771698853192,"version":"3.50.1"},"reference-count":43,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9687871","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"1011-1018","source":"Crossref","is-referenced-by-count":44,"title":["Scaling End-to-End Models for Large-Scale Multilingual ASR"],"prefix":"10.1109","author":[{"given":"Bo","family":"Li","sequence":"first","affiliation":[{"name":"Google,USA"}]},{"given":"Ruoming","family":"Pang","sequence":"additional","affiliation":[{"name":"Google,USA"}]},{"given":"Tara N.","family":"Sainath","sequence":"additional","affiliation":[{"name":"Google,USA"}]},{"given":"Anmol","family":"Gulati","sequence":"additional","affiliation":[{"name":"Google,USA"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google,USA"}]},{"given":"James","family":"Qin","sequence":"additional","affiliation":[{"name":"Google,USA"}]},{"given":"Parisa","family":"Haghani","sequence":"additional","affiliation":[{"name":"Google,USA"}]},{"given":"W. Ronny","family":"Huang","sequence":"additional","affiliation":[{"name":"Google,USA"}]},{"given":"Min","family":"Ma","sequence":"additional","affiliation":[{"name":"Google,USA"}]},{"given":"Junwen","family":"Bai","sequence":"additional","affiliation":[{"name":"Google,USA"}]}],"member":"263","reference":[{"key":"ref39","first-page":"4596","article-title":"Adafactor: Adaptive learning rates with sublinear memory cost","author":"shazeer","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref38","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc ICLR"},{"key":"ref33","article-title":"Listen, attend and spell","volume":"abs 1508 1211","author":"chan","year":"2015","journal-title":"CoRR"},{"key":"ref32","article-title":"Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling","author":"sak","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413899"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref37","author":"abadi","year":"2015","journal-title":"Tensorflow Large-scale machine learning on heterogeneous distributed systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref35","article-title":"Lingvo: a modular and scalable framework for sequence-to-sequence modeling","author":"shen","year":"2019","journal-title":"ArXiv"},{"key":"ref34","article-title":"Attention Is All You Need","volume":"abs 1706 3762","author":"vaswani","year":"2017","journal-title":"CoRR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2846"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2059"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414716"},{"key":"ref15","article-title":"Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges","author":"arivazhagan","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461886"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2858"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682674"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2831"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-65414-6_13"},{"key":"ref4","article-title":"Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition","author":"zhang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref27","article-title":"Gradient vaccine: Investigating and improving multi-task optimization in massively multilingual models","author":"wang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref3","article-title":"Language Models are Few-Shot Learners","author":"brown","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref6","article-title":"Computer-coding the IPA: a proposed extension of SAMPA","volume":"4","author":"wells","year":"1995","journal-title":"Revised Draft"},{"key":"ref29","article-title":"Scaling laws for neural language models","author":"kaplan","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref5","year":"1999","journal-title":"Handbook of the International Phonetic Association A Guide to the Use of the International Phonetic Alphabet"},{"key":"ref8","article-title":"ASR-articulatory speech recognition","author":"frankel","year":"0","journal-title":"Seventh European Conference on Speech Communication and Technology"},{"key":"ref7","first-page":"72","article-title":"ASCII phonetic symbols for the world's languages: Worldbet","volume":"23","author":"hieronymus","year":"1993","journal-title":"Journal of the International Phonetic Association"},{"key":"ref2","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","author":"devlin","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref1","article-title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","author":"lepikhin","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2164"},{"key":"ref22","article-title":"Multilingual end-to-end speech recognition with a single transformer on low-resource languages","author":"zhou","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1009"},{"key":"ref42","article-title":"Unsupervised cross-lingual representation learning for speech recognition","author":"conneau","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.754"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref23","author":"chuangsuwanich","year":"2016","journal-title":"Multilingual Techniques for Low Resource Automatic Speech Recognition"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1007379606734","article-title":"Multitask learning","volume":"28","author":"caruana","year":"1997","journal-title":"Machine Learning"},{"key":"ref43","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"ArXiv Preprint"},{"key":"ref25","author":"mitchell","year":"1980","journal-title":"The need for biases in learning generalizations"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Cartagena, Colombia","start":{"date-parts":[[2021,12,13]]},"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\/09687871.pdf?arnumber=9687871","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:42:02Z","timestamp":1652733722000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9687871\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9687871","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}