{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:08:25Z","timestamp":1765357705362,"version":"3.27.0"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,25]],"date-time":"2024-09-25T00:00:00Z","timestamp":1727222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,25]],"date-time":"2024-09-25T00:00:00Z","timestamp":1727222400000},"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":[[2024,9,25]]},"DOI":"10.23919\/spa61993.2024.10715611","type":"proceedings-article","created":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T17:29:18Z","timestamp":1729186158000},"page":"155-160","source":"Crossref","is-referenced-by-count":1,"title":["Automatic re-labeling of Google AudioSet for improved quality of learned features and pre-training"],"prefix":"10.23919","author":[{"given":"Tomasz","family":"Grzywalski","sequence":"first","affiliation":[{"name":"Ghent University,Department of Information Technology,Ghent,Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dick","family":"Botteldooren","sequence":"additional","affiliation":[{"name":"Ghent University,Department of Information Technology,Ghent,Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"volume-title":"AudioSet \u2014 research.google.com","year":"2023","key":"ref2"},{"volume-title":"Efficient audio captioning transformer with patchout and text guidance","year":"2023","author":"Kouzelis","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1515\/noise-2019-0005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO58844.2023.10289815"},{"volume-title":"Parsing birdsong with deep audio embeddings","year":"2021","author":"Tolkova","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC44109.2020.9175450"},{"volume-title":"Diffusion models as masked audio-video learners","year":"2023","author":"Nunez","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616087"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3006378"},{"volume-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref15"}],"event":{"name":"2024 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","start":{"date-parts":[[2024,9,25]]},"location":"Poznan, Poland","end":{"date-parts":[[2024,9,27]]}},"container-title":["2024 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10715565\/10715594\/10715611.pdf?arnumber=10715611","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T04:46:07Z","timestamp":1729226767000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10715611\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,25]]},"references-count":15,"URL":"https:\/\/doi.org\/10.23919\/spa61993.2024.10715611","relation":{},"subject":[],"published":{"date-parts":[[2024,9,25]]}}}