{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T07:21:27Z","timestamp":1763018487977},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746594","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6397-6401","source":"Crossref","is-referenced-by-count":24,"title":["Massively Multilingual ASR: A Lifelong Learning Solution"],"prefix":"10.1109","author":[{"given":"Bo","family":"Li","sequence":"first","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Ruoming","family":"Pang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Tara N.","family":"Sainath","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Trevor","family":"Strohman","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Parisa","family":"Haghani","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Yun","family":"Zhu","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Brian","family":"Farris","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Neeraj","family":"Gaur","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Manasa","family":"Prasad","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]}],"member":"263","reference":[{"key":"ref38","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":"ref33","article-title":"Attention Is All You Need","author":"vaswani","year":"2017","journal-title":"CoRR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413899"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"article-title":"An empirical investigation of catastrophic forgeting in gradient-based neural networks","year":"2013","author":"bengio","key":"ref30"},{"article-title":"Lingvo: a modular and scalable framework for sequence-to-sequence modeling","year":"2019","author":"shen","key":"ref37"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"article-title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","year":"2020","author":"lepikhin","key":"ref35"},{"year":"0","key":"ref34","article-title":"Cloud Tensor Processing Units (TPUs"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref11","article-title":"Listen, attend and spell","author":"chan","year":"2015","journal-title":"CoRR"},{"article-title":"Sequence transduction with recurrent neural networks","year":"2012","author":"graves","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414716"},{"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"},{"article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","year":"2019","author":"raffel","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414922"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003906"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01294-2"},{"key":"ref5","article-title":"Exploring neural transducers for end-to-end speech recognition","author":"battenberg","year":"2017","journal-title":"Proc ASRU"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2846"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1855"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-654"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref1","article-title":"Attention-Based Models for Speech Recognition","author":"chorowski","year":"2015","journal-title":"Proc NIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2164"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687871"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1009"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"article-title":"A configurable multilingual model is all you need to recognize all languages","year":"2021","author":"zhou","key":"ref23"},{"article-title":"BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition","year":"2021","author":"yu","key":"ref26"},{"article-title":"On the opportunities and risks of foundation models","year":"2021","author":"bommasani","key":"ref25"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746594.pdf?arnumber=9746594","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:05:32Z","timestamp":1660593932000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746594\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746594","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}