{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:54:47Z","timestamp":1753602887152,"version":"3.28.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389657","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["Generalized Zero-Shot Audio-to-Intent Classification"],"prefix":"10.1109","author":[{"given":"Veera Raghavendra","family":"Elluru","sequence":"first","affiliation":[{"name":"AWS AI Labs"}]},{"given":"Devang","family":"Kulshreshtha","sequence":"additional","affiliation":[{"name":"AWS AI Labs"}]},{"given":"Rohit","family":"Paturi","sequence":"additional","affiliation":[{"name":"AWS AI Labs"}]},{"given":"Sravan","family":"Bodapati","sequence":"additional","affiliation":[{"name":"AWS AI Labs"}]},{"given":"Srikanth","family":"Ronanki","sequence":"additional","affiliation":[{"name":"AWS AI Labs"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-60366-7_23"},{"key":"ref2","article-title":"Designing voice user interfaces: Principles of conversational experiences","author":"Pearl","year":"2016","journal-title":"O\u2019Reilly Media, Inc"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639043"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461718"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-836"},{"key":"ref6","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1873"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747754"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414996"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414922"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref13","article-title":"A Fine-tuned Wav2vec 2.0\/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding","author":"Wang","year":"2022","journal-title":"arXiv preprint arXiv:2111.02735"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.402"},{"key":"ref15","article-title":"Zero-Shot Learning with Semantic Output Codes","volume":"22","author":"Palatucci","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/0921-4534(95)00110-7"},{"key":"ref17","first-page":"5542","article-title":"Feature Generating Networks for ZeroShot Learning","volume-title":"Proc. CVPR","author":"Xian"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00717"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00240"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3065234"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.23919\/eusipco55093.2022.9909760"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3302506.3310402"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_2"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462985"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00373"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023147"},{"article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin","key":"ref27"},{"key":"ref28","first-page":"16857","article-title":"Mpnet: Masked and permuted pre-training for language understanding","volume":"33","author":"Song","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095889"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1136"},{"key":"ref31","first-page":"8748","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"International conference on machine learning","author":"Radford"},{"volume-title":"Amazon Polly","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.588"},{"key":"ref34","article-title":"Interpreting and Explaining Deep Neural Networks for Classification of Audio Signals","author":"Becker","year":"2018","journal-title":"arXiv preprint arXiv:1807.034183"},{"key":"ref35","article-title":"TIMIT Acoustic-Phonetic Continuous Speech Corpus","author":"Garofolo","year":"1993","journal-title":"Linguistic Data Consortium, 1993"},{"key":"ref36","article-title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","author":"Warden","year":"2018","journal-title":"arXiv preprint arXiv:1804.03209"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746250"},{"volume-title":"Hubert-Large","year":"2023","author":"Face","key":"ref38"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2023,12,16]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389657.pdf?arnumber=10389657","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:35:46Z","timestamp":1706027746000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389657\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389657","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}