{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:45:27Z","timestamp":1772909127301,"version":"3.50.1"},"reference-count":21,"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\/icassp49357.2023.10096950","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":["Adaptive Knowledge Distillation Between Text and Speech Pre-Trained Models"],"prefix":"10.1109","author":[{"given":"Jinjie","family":"Ni","sequence":"first","affiliation":[{"name":"Alibaba Group"}]},{"given":"Yukun","family":"Ma","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Wen","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Qian","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Dianwen","family":"Ng","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Han","family":"Lei","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,School of Computer Science and Engineering"}]},{"given":"Trung Hieu","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Chong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Bin","family":"Ma","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Erik","family":"Cambria","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,School of Computer Science and Engineering"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Slam: A unified encoder for speech and language modeling via speech-text joint pretraining","author":"bapna","year":"2021"},{"key":"ref12","article-title":"Calm: Contrastive aligned audio-language multirate and multimodal representations","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747759"},{"key":"ref14","article-title":"mslam: Massively multilingual joint pre-training for speech and text","author":"bapna","year":"2022"},{"key":"ref20","article-title":"Lite transformer with long-short range attention","author":"wu","year":"0"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.393"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref2","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","author":"lan","year":"0"},{"key":"ref1","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"2019","journal-title":"Proceedings of the NAACL-HLT 2019"},{"key":"ref17","first-page":"881","article-title":"Pretrained semantic speech embeddings for end-to-end spoken language understanding via cross-modal teacher-student learning","author":"denisov","year":"2020","journal-title":"Interspeech 2020 21st Annual Conference of the International Speech Communication Association Virtual Event"},{"key":"ref16","article-title":"Cross-modal discrete representation learning","author":"liu","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.469"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.152"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref7","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"NeurIPS 2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.09.029"},{"key":"ref4","first-page":"140:1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"raffel","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref3","article-title":"Roberta: A robustly optimized BERT pretraining approach","author":"liu","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref5","article-title":"Language models are unsupervised multitask learners","author":"radford","year":"2019"}],"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\/10096950.pdf?arnumber=10096950","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T18:57:56Z","timestamp":1700506676000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096950\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096950","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}