{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T18:07:48Z","timestamp":1758823668366,"version":"3.38.0"},"reference-count":24,"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"}],"funder":[{"DOI":"10.13039\/501100001475","name":"Nanyang Technological University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001475","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096976","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":10,"title":["Contrastive Speech Mixup for Low-Resource Keyword Spotting"],"prefix":"10.1109","author":[{"given":"Dianwen","family":"Ng","sequence":"first","affiliation":[{"name":"Alibaba Group"}]},{"given":"Ruixi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Jia Qi","family":"Yip","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Chong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Yukun","family":"Ma","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Trung Hieu","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Chongjia","family":"Ni","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Eng Siong","family":"Chng","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,School of Computer Science and Engineering,Singapore"}]},{"given":"Bin","family":"Ma","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1453\/1\/012085"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref14","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414483"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747755"},{"article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","year":"2018","author":"warden","key":"ref22"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2891838"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3196562"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-352"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980261"},{"key":"ref16","article-title":"Co-mixup: Saliency guided joint mixup with super-modular diversity","author":"kim","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref19","first-page":"6438","article-title":"Manifold mixup: Better representations by interpolating hidden states","author":"verma","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746314"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1363"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1003"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746535"},{"article-title":"Small footprint multi-channel con-vmixer for keyword spotting with centroid based awareness","year":"2022","author":"ng","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747295"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1286"}],"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\/10096976.pdf?arnumber=10096976","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T18:42:19Z","timestamp":1740681739000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096976\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096976","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}