{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:28:53Z","timestamp":1775230133228,"version":"3.50.1"},"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\/icassp43922.2022.9747025","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"3603-3607","source":"Crossref","is-referenced-by-count":47,"title":["Convmixer: Feature Interactive Convolution with Curriculum Learning for Small Footprint and Noisy Far-Field Keyword Spotting"],"prefix":"10.1109","author":[{"given":"Dianwen","family":"Ng","sequence":"first","affiliation":[{"name":"Alibaba Group,Beijing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunqi","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group,Beijing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Biao","family":"Tian","sequence":"additional","affiliation":[{"name":"Alibaba Group,Beijing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Fu","sequence":"additional","affiliation":[{"name":"Alibaba Group,Beijing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eng Siong","family":"Chng","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,School of Computer Science and Engineering,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-352"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref12","article-title":"Hello edge: Keyword spotting on microcontrollers","author":"zhang","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081267"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2765832"},{"key":"ref15","article-title":"Searching for activation functions","author":"ramachandran","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-383"},{"key":"ref17","article-title":"FNet: Mixing Tokens with Fourier Transforms","author":"lee-thorp","year":"2021"},{"key":"ref18","article-title":"MLP-Mixer: An all-MLP Architecture for Vision","author":"tolstikhin","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462688"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178863"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1737"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1420"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846261"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1286"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1003"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1058"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854370"},{"key":"ref20","article-title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","author":"warden","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2917582"},{"key":"ref21","article-title":"MUSAN: A Music, Speech, and Noise Corpus","author":"david","year":"2015"}],"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\/09747025.pdf?arnumber=9747025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:14:50Z","timestamp":1661199290000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747025\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747025","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}