{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:18:14Z","timestamp":1776885494148,"version":"3.51.2"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746137","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7927-7931","source":"Crossref","is-referenced-by-count":37,"title":["SLUE: New Benchmark Tasks For Spoken Language Understanding Evaluation on Natural Speech"],"prefix":"10.1109","author":[{"given":"Suwon","family":"Shon","sequence":"first","affiliation":[{"name":"Asapp"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ankita","family":"Pasad","sequence":"additional","affiliation":[{"name":"Toyota Technological Institute at Chicago"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Felix","family":"Wu","sequence":"additional","affiliation":[{"name":"Asapp"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pablo","family":"Brusco","sequence":"additional","affiliation":[{"name":"Asapp"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoav","family":"Artzi","sequence":"additional","affiliation":[{"name":"Asapp"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karen","family":"Livescu","sequence":"additional","affiliation":[{"name":"Toyota Technological Institute at Chicago"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyu J.","family":"Han","sequence":"additional","affiliation":[{"name":"Asapp"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052937"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-0429"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2444"},{"key":"ref32","article-title":"A large scale speech sentiment corpus","author":"chen","year":"2020","journal-title":"LREC"},{"key":"ref31","article-title":"Multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph","author":"zadeh","year":"2018","journal-title":"ACL"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref37","article-title":"End-To-End Named Entity and Semantic Concept Extraction from Speech","author":"ghannay","year":"2019","journal-title":"SLT"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00197"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-2025"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2482"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053176"},{"key":"ref11","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053541"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref15","article-title":"Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition","author":"wu","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2380"},{"key":"ref17","article-title":"Augmen-tation adversarial training for self-supervised speaker recognition","author":"huh","year":"2020","journal-title":"NeurIPS SAS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053163"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413910"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-010-9120-1"},{"key":"ref4","article-title":"ASR-GLUE: A New Multi-task Benchmark for ASR-Robust Natural Language Understanding","author":"feng","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3115\/116580.116613"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref6","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"liu","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414922"},{"key":"ref5","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref7","article-title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","author":"he","year":"2020","journal-title":"ICLRE"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref9","article-title":"Improving Transformer-based Speech Recognition Using Unsupervised Pre-training","author":"jiang","year":"2019"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462685"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref21","article-title":"Representation Learning with Contrastive Predictive Coding","author":"van den oord","year":"2018"},{"key":"ref24","article-title":"Speech model pre-training for end-to-end spoken language under-standing","author":"lugosch","year":"2019","journal-title":"InterSpeech"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"VoxCeleb: A large-scale speaker identification dataset","author":"nagraniy","year":"2017","journal-title":"InterSpeech"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383575"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/1614049.1614064"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01132-1"},{"key":"ref25","article-title":"Snips voice platform: an embedded spoken language understanding system for private-by-design voice interfaces","author":"coucke","year":"2018"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746137.pdf?arnumber=9746137","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:05:43Z","timestamp":1660593943000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746137\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746137","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}