{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:44:26Z","timestamp":1730231066045,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446276","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10776-10780","source":"Crossref","is-referenced-by-count":0,"title":["Zero-Shot Intent Classification Using a Semantic Similarity Aware Contrastive Loss and Large Language Model"],"prefix":"10.1109","author":[{"given":"Jaejin","family":"Cho","sequence":"first","affiliation":[{"name":"Samsung Research America,CA,USA"}]},{"given":"Rakshith Sharma","family":"Srinivasa","sequence":"additional","affiliation":[{"name":"Samsung Research America,CA,USA"}]},{"given":"Ching-Hua","family":"Lee","sequence":"additional","affiliation":[{"name":"Samsung Research America,CA,USA"}]},{"given":"Yashas Malur","family":"Saidutta","sequence":"additional","affiliation":[{"name":"Samsung Research America,CA,USA"}]},{"given":"Chouchang","family":"Yang","sequence":"additional","affiliation":[{"name":"Samsung Research America,CA,USA"}]},{"given":"Yilin","family":"Shen","sequence":"additional","affiliation":[{"name":"Samsung Research America,CA,USA"}]},{"given":"Hongxia","family":"Jin","sequence":"additional","affiliation":[{"name":"Samsung Research America,CA,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1826"},{"key":"ref2","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2857768"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01274"},{"key":"ref6","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747674"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.588"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"article-title":"Listen, think, and understand","year":"2023","author":"Gong","key":"ref10"},{"key":"ref11","first-page":"689","article-title":"Multimodal deep learning","volume-title":"International conference on machine learning","author":"Ngiam"},{"key":"ref12","first-page":"1247","article-title":"Deep canonical correlation analysis","volume-title":"International conference on machine learning","author":"Andrew"},{"key":"ref13","first-page":"1083","article-title":"On deep multi-view representation learning","volume-title":"International conference on machine learning","author":"Wang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_40"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053281"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747759"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-788"},{"article-title":"Common voice: A massively-multilingual speech corpus","year":"2019","author":"Ardila","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/EMC2-NIPS53020.2019.00021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022703"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"article-title":"Robust speech recognition via large-scale weak supervision","year":"2022","author":"Radford","key":"ref24"},{"article-title":"Finetuned language models are zero-shot learners","volume-title":"International Conference on Learning Representations","author":"Wei","key":"ref25"},{"article-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023","author":"Touvron","key":"ref26"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446276.pdf?arnumber=10446276","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:08:55Z","timestamp":1722575335000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446276\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446276","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}