{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T04:11:15Z","timestamp":1748059875754,"version":"3.28.0"},"reference-count":22,"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\/icassp43922.2022.9746266","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"321-325","source":"Crossref","is-referenced-by-count":5,"title":["Improved Representation Learning For Acoustic Event Classification Using Tree-Structured Ontology"],"prefix":"10.1109","author":[{"given":"Arman","family":"Zharmagambetov","sequence":"first","affiliation":[{"name":"University of California,Merced"}]},{"given":"Qingming","family":"Tang","sequence":"additional","affiliation":[{"name":"Amazon Alexa"}]},{"given":"Chieh-Chi","family":"Kao","sequence":"additional","affiliation":[{"name":"Amazon Alexa"}]},{"given":"Qin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Amazon Alexa"}]},{"given":"Ming","family":"Sun","sequence":"additional","affiliation":[{"name":"Amazon Alexa"}]},{"given":"Viktor","family":"Rozgic","sequence":"additional","affiliation":[{"name":"Amazon Alexa"}]},{"given":"Jasha","family":"Droppo","sequence":"additional","affiliation":[{"name":"Amazon Alexa"}]},{"given":"Chao","family":"Wang","sequence":"additional","affiliation":[{"name":"Amazon Alexa"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume":"abs 2006 9882","author":"caron","year":"2020","journal-title":"ArXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref12","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","volume":"33","author":"xie","year":"2020","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref13","article-title":"Unsupervised speech recognition via segmental empirical output distribution matching","volume":"abs 1812 9323","author":"yeh","year":"2019","journal-title":"ArXiv"},{"article-title":"Unsupervised speech recognition","year":"2021","author":"baevski","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00590"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937283"},{"key":"ref17","article-title":"Sound event classification using ontology-based neural networks","author":"jimenez","year":"2018","journal-title":"NeurIPS Workshop on Interpretability and Robustness in Audio Speech and Language"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053389"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.172"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1228"},{"key":"ref8","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref7","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref2","article-title":"Acoustic event detection and classification in smart-room environments: Evaluation of CHIL project systems","author":"temko","year":"2006","journal-title":"The IV Biennial Workshop on Speech Technology"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CWIT.2015.7255156"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413718"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref21","article-title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","volume":"abs 2001 7685","author":"sohn","year":"2020","journal-title":"ArXiv"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","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\/09746266.pdf?arnumber=9746266","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:14:47Z","timestamp":1661199287000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746266\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746266","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}