{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T06:34:07Z","timestamp":1723530847758},"reference-count":26,"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\/icassp49357.2023.10094997","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"source":"Crossref","is-referenced-by-count":4,"title":["Fine-Grained Textual Knowledge Transfer to Improve RNN Transducers for Speech Recognition and Understanding"],"prefix":"10.1109","author":[{"given":"Vishal","family":"Sunder","sequence":"first","affiliation":[{"name":"The Ohio State University"}]},{"given":"Samuel","family":"Thomas","sequence":"additional","affiliation":[{"name":"IBM Research AI"}]},{"given":"Hong-Kwang J.","family":"Kuo","sequence":"additional","affiliation":[{"name":"IBM Research AI"}]},{"given":"Brian","family":"Kingsbury","sequence":"additional","affiliation":[{"name":"IBM Research AI"}]},{"given":"Eric","family":"Fosler-Lussier","sequence":"additional","affiliation":[{"name":"The Ohio State University"}]}],"member":"263","reference":[{"key":"ref13","author":"ravanelli","year":"2021","journal-title":"SpeechBrain A General-Purpose Speech Toolkit"},{"key":"ref12","article-title":"SPLAT: Speechlanguage joint pre-training for spoken language understanding","author":"chung","year":"2020","journal-title":"NAACL"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11067"},{"key":"ref14","author":"wang","year":"2021","journal-title":"A fine-tuned wav2vec 2 0\/hubert benchmark for speech emotion recognition speaker verification and spoken language understanding"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747871"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747759"},{"key":"ref2","author":"graves","year":"2012","journal-title":"Sequence transduction with recurrent neural networks"},{"key":"ref1","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414716"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747760"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414029"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2924"},{"key":"ref24","article-title":"Decoupled weight decay regularization","author":"loschilov","year":"2019","journal-title":"ICLRE"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683706"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747047"},{"key":"ref25","author":"smith","year":"2017","journal-title":"Super-convergence Very fast training of neural networks using large learning rates"},{"key":"ref20","author":"bastianelli","year":"2020","journal-title":"Slurp A spoken language understanding resource package"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2456"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-239"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053281"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1179"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746801"},{"key":"ref6","author":"higuchi","year":"2022","journal-title":"BERT meets CTC New formulation of end-to-end speech recognition with pre-trained masked language model"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-716"}],"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\/10094997.pdf?arnumber=10094997","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:05:05Z","timestamp":1700507105000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094997\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094997","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}