{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T16:13:17Z","timestamp":1764259997008,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,3]]},"DOI":"10.1109\/icassp.2017.7952263","type":"proceedings-article","created":{"date-parts":[[2017,6,20]],"date-time":"2017-06-20T17:35:36Z","timestamp":1497980136000},"page":"786-790","source":"Crossref","is-referenced-by-count":26,"title":["Large-scale audio event discovery in one million YouTube videos"],"prefix":"10.1109","author":[{"given":"Aren","family":"Jansen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jort F.","family":"Gemmeke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel P. W.","family":"Ellis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofeng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wade","family":"Lawrence","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dylan","family":"Freedman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1178","article-title":"Unsupervised structure discovery for semantic analysis of audio","author":"chaudhuri","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref11","first-page":"1277","article-title":"Acoustic stopwords for unstructured audio information retrieval","author":"kim","year":"2010","journal-title":"Proceedings of European Signal Processing Conference"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552989"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2027216.2027217"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972764.29"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/276698.276876"},{"key":"ref16","article-title":"Audio set: A strongly labeled dataset of audio events","author":"gemmeke","year":"2017","journal-title":"Proc ICA SSP"},{"journal-title":"Google I\/O2013 — semantic video annotations in the Youtube Topics API Theory and applications","year":"0","key":"ref17"},{"journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition","year":"2014","author":"simonyan","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-123"},{"key":"ref3","first-page":"35","article-title":"Bidirectional LSTM-HMM hybrid system for polyphonic sound event detection","author":"hayashi","year":"2016","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2016 Workshop (DCASE2016)"},{"key":"ref6","first-page":"311","article-title":"Clear evaluation of acoustic event detection and classification systems","author":"temko","year":"2006","journal-title":"Classification of Events Activities and Relationships Evaluation and Workshop"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref8","first-page":"2105","article-title":"Bag-of-audio-words approach for multimedia event classification","author":"pancoast","year":"2012","journal-title":"Proceedings of Interspeech"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701847"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6287923"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853821"},{"key":"ref20","first-page":"410","article-title":"V-measure: A conditional entropy-based external cluster evaluation measure","volume":"7","author":"rosenberg","year":"2007","journal-title":"Proceedings of EMNLP-CoNLL"}],"event":{"name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2017,3,5]]},"location":"New Orleans, LA","end":{"date-parts":[[2017,3,9]]}},"container-title":["2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7943262\/7951776\/07952263.pdf?arnumber=7952263","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,8,29]],"date-time":"2017-08-29T14:48:03Z","timestamp":1504018083000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7952263\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp.2017.7952263","relation":{},"subject":[],"published":{"date-parts":[[2017,3]]}}}