{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:41:03Z","timestamp":1730230863595,"version":"3.28.0"},"reference-count":25,"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\/icassp49357.2023.10096418","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":2,"title":["Comparison of Soft and Hard Target RNN-T Distillation for Large-Scale ASR"],"prefix":"10.1109","author":[{"given":"Dongseong","family":"Hwang","sequence":"first","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Khe","family":"Chai Sim","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Trevor","family":"Strohman","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-614"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413905"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414641"},{"article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","year":"2020","author":"zhang","key":"ref10"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413899"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054188"},{"article-title":"Self-supervised learning with random-projection quantizer for speech recognition","year":"2022","author":"chiu","key":"ref17"},{"article-title":"Why distillation helps: a statistical perspective","year":"2005","author":"menon","key":"ref16"},{"key":"ref19","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639610"},{"key":"ref23","first-page":"6010","article-title":"Searching for efficient transformers for language modeling","volume":"34","author":"so","year":"2021","journal-title":"Advances in neural information processing systems"},{"year":"0","key":"ref25","article-title":"Artificial intelligence at google: Our principles"},{"key":"ref20","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","volume":"33","author":"xie","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"article-title":"Solving imagenet: a unified scheme for training any backbone to top results","year":"2022","author":"ridnik","key":"ref21"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3182537"},{"key":"ref7","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"International Conference on Machine Learning Representation Learning Workshop"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11034"},{"key":"ref4","article-title":"Distilling the knowledge in a neural network","volume":"2","author":"hinton","year":"2015"},{"key":"ref3","first-page":"920","article-title":"Recognizing long-form speech using streaming end-to-end models","author":"narayanan","year":"2019","journal-title":"Proc IEEE Workshop Automatic Speech Recognition and Understanding (ASRU)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","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\/10096418.pdf?arnumber=10096418","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T17:57:27Z","timestamp":1698083847000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096418\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096418","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}