{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T10:07:33Z","timestamp":1760609253042,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[[2019,12]]},"DOI":"10.1109\/asru46091.2019.9003962","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T07:01:33Z","timestamp":1582268493000},"page":"660-666","source":"Crossref","is-referenced-by-count":4,"title":["End-to-End Overlapped Speech Detection and Speaker Counting with Raw Waveform"],"prefix":"10.1109","author":[{"given":"Wangyou","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Man","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2910759"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461267"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462548"},{"journal-title":"Batch Normalization Accelerating Deep Network Training by Reducing Internal Covariate Shift","year":"2015","author":"ioffe","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref15","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in English and Mandarin","author":"amodei","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462159"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1109\/TASLP.2018.2877892","article-title":"CountNet: Estimating the number of concurrent speakers using supervised learning","volume":"27","author":"st\u00f6ter","year":"2018","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1749"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518619"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5745511"},{"key":"ref5","article-title":"Sound event localization and detection of overlapping sources using convolutional recurrent neural networks","author":"adavanne","year":"2018","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"ref8","first-page":"84","article-title":"Speech and crosstalk detection in multichannel audio","volume":"13","author":"stuart","year":"2004","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"ref7","article-title":"Probabilistic linear discriminant analysis for robust speaker identification in co-channel speech","author":"shokouhi","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1037\/0735-7036.122.3.235"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907229"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472766"}],"event":{"name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2019,12,14]]},"location":"SG, Singapore","end":{"date-parts":[[2019,12,18]]}},"container-title":["2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8985378\/9003727\/09003962.pdf?arnumber=9003962","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T14:49:25Z","timestamp":1658155765000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9003962\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/asru46091.2019.9003962","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}