{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T11:05:10Z","timestamp":1786100710740,"version":"3.56.0"},"reference-count":23,"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\/icassp43922.2022.9746828","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"151-155","source":"Crossref","is-referenced-by-count":44,"title":["Vocalsound: A Dataset for Improving Human Vocal Sounds Recognition"],"prefix":"10.1109","author":[{"given":"Yuan","family":"Gong","sequence":"first","affiliation":[{"name":"MIT CSAIL,Cambridge,MA,USA,02139"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Yu","sequence":"additional","affiliation":[{"name":"Signify Research,Cambridge,MA,USA,02142"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Glass","sequence":"additional","affiliation":[{"name":"MIT CSAIL,Cambridge,MA,USA,02139"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"A closer look at weak label learning for audio events","author":"shah","year":"2018"},{"key":"ref11","article-title":"Dcase 2017 challenge setup: Tasks, datasets and baseline system","author":"mesaros","year":"2017","journal-title":"DCAS"},{"key":"ref12","article-title":"The coughvid crowdsourcing dataset: A corpus for the study of large-scale cough analysis algorithms","author":"orlandic","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/OJEMB.2020.3026928"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3412865"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3018028"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2020.100378"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-19"},{"key":"ref18","article-title":"Cough against covid: Evidence of covid-19 signature in cough sounds","author":"bagad","year":"2020"},{"key":"ref19","article-title":"Vocal imitation set: a dataset of vocally imitated sound events using the audioset ontology","author":"kim","year":"2018","journal-title":"DCAS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2030112.2030163"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3120633"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref8","article-title":"Fsd50k: an open dataset of human-labeled sound events","author":"fonseca","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/Eusipco47968.2020.9287659"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1159\/000504666"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3006378"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702387"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref21","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"ICML"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"}],"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\/09746828.pdf?arnumber=9746828","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:11:39Z","timestamp":1660594299000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746828\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746828","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}