{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:11:25Z","timestamp":1775578285997,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,11,18]],"date-time":"2021-11-18T00:00:00Z","timestamp":1637193600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,11,18]],"date-time":"2021-11-18T00:00:00Z","timestamp":1637193600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,11,18]],"date-time":"2021-11-18T00:00:00Z","timestamp":1637193600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","award":["A18A2b0046"],"award-info":[{"award-number":["A18A2b0046"]}],"id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005049","name":"Science and Engineering Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005049","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,11,18]]},"DOI":"10.1109\/o-cocosda202152914.2021.9660517","type":"proceedings-article","created":{"date-parts":[[2022,1,3]],"date-time":"2022-01-03T20:19:17Z","timestamp":1641241157000},"page":"128-133","source":"Crossref","is-referenced-by-count":2,"title":["SLoClas: A Database for Joint Sound Localization and Classification"],"prefix":"10.1109","author":[{"given":"Xinyuan","family":"Qian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bidisha","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amine","family":"El Abridi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2901664"},{"key":"ref32","first-page":"2565","author":"florencio","year":"2008","journal-title":"Why does PHAT work well in low noise reverberant environment"},{"key":"ref31","first-page":"320","volume":"24","author":"knapp","year":"1976","journal-title":"The generalized correlation method for estimation of time delay"},{"key":"ref30","article-title":"Multi-tones' phase coding (mtpc) of interaural time difference by spiking neural network","author":"pan","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref35","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref34","first-page":"320","volume":"24","author":"knapp","year":"1976","journal-title":"The generalized correlation method for estimation of time delay"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-015-3105-4"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2470216"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170028"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553182"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2900164"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2907016"},{"key":"ref16","article-title":"Poly-phonic sound event detection and localization using a two-stage strategy","author":"cao","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref17","article-title":"Classification of spatial audio location and content using convolutional neural networks","author":"hirvonen","year":"2015","journal-title":"Audio Engineering Society Convention 138"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref19","author":"nakamura","year":"2000","journal-title":"Acoustical sound database in real environments for sound scene understanding and hands-free speech recognition"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.2015.7373137"},{"key":"ref4","first-page":"2814","author":"qian","year":"2021","journal-title":"Multi-target doa estimation with an audio-visual fusion mechanism"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-790"},{"key":"ref3","first-page":"74","author":"wang","year":"2021","journal-title":"GCC-PHAT with speech-oriented attention for robotic sound source localization"},{"key":"ref6","first-page":"74","article-title":"Is someone speaking? exploring long-term temporal features for audio-visual active speaker detection","author":"tao","year":"2021","journal-title":"ACM Multimedia"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2641901"},{"key":"ref5","first-page":"1404","author":"qiquan","year":"2021","journal-title":"DeepMMSE A deep learning approach to mmse-based noise power spectral density estimation"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2007.4425280"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IECON.2017.8217063"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1928"},{"key":"ref9","first-page":"1317","article-title":"Two-source acoustic event detection and localization: Online implementation in a smart-room","author":"butko","year":"0","journal-title":"2011 19th European Signal Processing Conference"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846325"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.07.002"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/O-COCOSDA46868.2019.9060842"},{"key":"ref21","first-page":"74","author":"he","year":"2018","journal-title":"Deep neural networks for multiple speaker detection and localization"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1121\/1.412224"},{"key":"ref23","article-title":"A dataset of reverberant spatial sound scenes with moving sources for sound event localization and detection","author":"politis","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref26","year":"0","journal-title":"Audacity"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"2067","DOI":"10.1109\/TASL.2010.2041110","article-title":"A tandem algorithm for pitch estimation and voiced speech segregation","volume":"18","author":"hu","year":"2010","journal-title":"IEEE Transactions on Audio Speech and Language Processing"}],"event":{"name":"2021 24th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","location":"Singapore, Singapore","start":{"date-parts":[[2021,11,18]]},"end":{"date-parts":[[2021,11,20]]}},"container-title":["2021 24th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9660212\/9660400\/09660517.pdf?arnumber=9660517","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:56:38Z","timestamp":1652201798000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9660517\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,18]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/o-cocosda202152914.2021.9660517","relation":{},"subject":[],"published":{"date-parts":[[2021,11,18]]}}}