{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:38:39Z","timestamp":1763192319932,"version":"3.45.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"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":[[2025,10,12]]},"DOI":"10.1109\/waspaa66052.2025.11230931","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:47Z","timestamp":1763146007000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Robust Speech Activity Detection in the Presence of Singing Voice"],"prefix":"10.1109","author":[{"given":"Philipp","family":"Grundhuber","sequence":"first","affiliation":[{"name":"Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany"}]},{"given":"Mhd Modar","family":"Halimeh","sequence":"additional","affiliation":[{"name":"Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany"}]},{"given":"Martin","family":"Strau\u00df","sequence":"additional","affiliation":[{"name":"Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany"}]},{"given":"Emanu\u00ebl A. P.","family":"Habets","sequence":"additional","affiliation":[{"name":"International Audio Laboratories,Erlangen,Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078609"},{"volume-title":"Yamnet","year":"2020","author":"Plakal","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687477"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/app9153140"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.084"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447037"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446581"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2959917"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855054"},{"key":"ref11","first-page":"121","article-title":"Exploring data augmentation for improved singing voice detection with neural networks","author":"Schl\u00fcter","year":"2015","journal-title":"ISMIR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3166262"},{"issue":"9","key":"ref13","article-title":"Research on singing voice detection based on a long-term recurrent convolutional network with vocal separation and temporal smoothing","volume-title":"Electronics","volume":"9","author":"Zhang","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1121\/10.0001526"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adm9797"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3190732"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3068045"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2018.8547084"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1609"},{"article-title":"MUSDB18-HQ - an uncompressed version of MUSDB18","year":"2019","author":"Rafii","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-153"},{"key":"ref22","first-page":"619","article-title":"MoisesDB: A dataset for source separation beyond 4-stems","volume-title":"Proc. of the International Society for Music Information Retrieval","author":"Pereira"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref24","first-page":"102949","article-title":"Data augmentation for speech separation","volume-title":"Speech Communication","volume":"152","author":"Alex","year":"2023"},{"article-title":"Adam: A method for stochastic optimization","volume-title":"International Conference on Learning Representations (ICLR)","author":"Kingma","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS61860.2024.10810675"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordhb\/9780199660773.013.13"}],"event":{"name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","start":{"date-parts":[[2025,10,12]]},"location":"Tahoe City, CA, USA","end":{"date-parts":[[2025,10,15]]}},"container-title":["2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11230875\/11230917\/11230931.pdf?arnumber=11230931","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:35:17Z","timestamp":1763192117000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11230931\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/waspaa66052.2025.11230931","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]}}}