{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:46:35Z","timestamp":1730231195864,"version":"3.28.0"},"reference-count":17,"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\/icassp49357.2023.10097130","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":0,"title":["Auxiliary Pooling Layer For Spoken Language Understanding"],"prefix":"10.1109","author":[{"given":"Yukun","family":"Ma","sequence":"first","affiliation":[{"name":"Alibaba Group"}]},{"given":"Trung Hieu","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Jinjie","family":"Ni","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,School of Computer Science and Engineering"}]},{"given":"Wen","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Qian","family":"Chen","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"}]}],"member":"263","reference":[{"key":"ref13","first-page":"9346","article-title":"Efficient representation learning via adaptive context pooling","author":"huang","year":"2022","journal-title":"International Conference on Machine Learning"},{"key":"ref12","article-title":"Ponet: Pooling network for efficient token mixing in long sequences","author":"tan","year":"2022","journal-title":"International Conference on Learning Representations"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref11","first-page":"17627","article-title":"Branchformer: Parallel mlp-attention architectures to capture local and global context for speech recognition and understanding","author":"peng","year":"2022","journal-title":"International Conference on Machine Learning"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref1","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":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414922"},{"article-title":"FILIP: fine-grained interactive language-image pre-training","year":"0","author":"yao","key":"ref8"},{"article-title":"Calm: Contrastive aligned audio-language multirate and multimodal representations","year":"2022","author":"sachidananda","key":"ref7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3082299"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747754"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11378"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.152"}],"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\/10097130.pdf?arnumber=10097130","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:01:36Z","timestamp":1700506896000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10097130\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10097130","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}