{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T20:41:20Z","timestamp":1761597680444},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2016,4,1]],"date-time":"2016-04-01T00:00:00Z","timestamp":1459468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Graduate School for Computing in Medicine and Life Sciences"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2016,4]]},"DOI":"10.1109\/taslp.2016.2530401","type":"journal-article","created":{"date-parts":[[2016,2,15]],"date-time":"2016-02-15T19:10:27Z","timestamp":1455563427000},"page":"807-822","source":"Crossref","is-referenced-by-count":25,"title":["Learning Representations for Nonspeech Audio Events Through Their Similarities to Speech Patterns"],"prefix":"10.1109","volume":"24","author":[{"given":"Huy","family":"Phan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lars","family":"Hertel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco","family":"Maass","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Radoslaw","family":"Mazur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alfred","family":"Mertins","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639248"},{"key":"ref72","first-page":"357","author":"paul","year":"0","journal-title":"Proc Speech Nat Lang Work"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref70","author":"gordon","year":"2005","journal-title":"Ethnologue Languages of the World"},{"key":"ref39","first-page":"2105","article-title":"Bag-of-audio-words approach for multimedia event classification","author":"pancoast","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref38","first-page":"506","article-title":"Recognition of acoustic events using deep neural networks","author":"gencoglu","year":"0","journal-title":"Proc Eur Signal Process Conf (EUSIPCO"},{"key":"ref33","first-page":"1178","article-title":"Unsupervised structure discovery for semantic analysis of audio","author":"chaudhuri","year":"0","journal-title":"Proc Neural Inf Process Syst (NIPS)"},{"key":"ref32","first-page":"1520","article-title":"Audio event detection based on layered symbolic sequence representations","author":"chin","year":"0","journal-title":"Proc Int Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6287923"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701847"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2389618"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2229986"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637759"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607191"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115900"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1994.1019"},{"key":"ref63","first-page":"2370","article-title":"Model-based processing for acoustic scene analysis","author":"nadeu","year":"0","journal-title":"Proc Eur Signal Process Conf (EUSIPCO)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854807"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2013.6636620"},{"key":"ref27","first-page":"2518","article-title":"Pooling robust shift-invariant sparse representations of acoustic signals","author":"huang","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-9794-4"},{"key":"ref29","first-page":"1","article-title":"A database and challenge for acoustic scene classification and event detection","author":"giannoulis","year":"0","journal-title":"Proc Eur Signal Process Conf (EUSIPCO)"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"ref68","first-page":"2211","article-title":"Multiple kernel learning algorithms","volume":"12","author":"gnen","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref69","first-page":"396","article-title":"Learning nonlinear combinations of kernels","author":"cortes","year":"0","journal-title":"Proc Neural Inf Process Syst (NIPS)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.914399"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2017438"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2011.6082331"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2010.2100380"},{"key":"ref24","article-title":"Auditory-based processing of communication sounds","author":"walters","year":"2011"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.851880"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1121\/1.2750160"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00011"},{"key":"ref50","article-title":"The HTK book (for HTK Version 3.4.1)","author":"young","year":"0"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2118753"},{"key":"ref59","first-page":"307","author":"young","year":"0","journal-title":"Proc Workshop Hum Lang Technol"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701819"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84882-054-8_7"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-69568-4_29"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1093\/ijl\/3.4.235"},{"key":"ref54","first-page":"849","article-title":"On spectral clustering: Analysis and an algorithm","author":"ng","year":"0","journal-title":"Proc Proc Neural Inf Process Syst (NIPS)"},{"key":"ref53","first-page":"163","article-title":"Label embedding trees for large multi-class tasks","author":"bengio","year":"0","journal-title":"Proc Proc Neural Inf Process Syst (NIPS)"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"ref10","first-page":"1096","article-title":"Unsupervised feature learning for audio classification using convolutional deep belief networks","author":"lee","year":"0","journal-title":"Proc Neural Inf Process Syst (NIPS)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853821"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3210-1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854293"},{"key":"ref13","first-page":"403","article-title":"Moving beyond feature design: Deep architectures and automatic feature learning in music informatics","author":"humphrey","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf (ISMIR)"},{"key":"ref14","first-page":"93","article-title":"The DARPA speech recognition research database: Specifications and status","author":"fisher","year":"1986","journal-title":"Proc DARPA Workshop Speech Recognit"},{"key":"ref15","article-title":"Feature selection for multimodal acoustic event detection","author":"butko","year":"0"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2012.6343802"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907786"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/89.365379"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(00)00048-0"},{"key":"ref4","author":"wang","year":"2006","journal-title":"Computational\ufffdAuditory Scene Analysis Principles Algorithms and Applications"},{"key":"ref3","author":"bregman","year":"1994","journal-title":"Auditory Scene Analysis The Perceptual Organization of Sound"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2326181"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2010.937498"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2367814"},{"key":"ref7","first-page":"631","article-title":"Exploring superframe co-occurrence for acoustic event recognition","author":"phan","year":"0","journal-title":"Proc 22nd Eur Signal Process Conf (EUSIPCO"},{"key":"ref49","volume":"1","author":"gales","year":"2008","journal-title":"The Application of Hidden Markov Models in Speech Recognition"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2226160"},{"key":"ref46","first-page":"3441","article-title":"Representing nonspeech audio signals through speech classification models","author":"phan","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1155\/2011\/485738"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/29.46546"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.02.002"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2023162"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.862024"},{"key":"ref44","first-page":"2375","article-title":"Multi-microphone fusion for detection of speech and acoustic events in smart spaces","author":"giannoulis","year":"0","journal-title":"Proc Eur Signal Process Conf (EUSIPCO"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7422174\/07407354.pdf?arnumber=7407354","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:02:26Z","timestamp":1642003346000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7407354\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,4]]},"references-count":73,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2016.2530401","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,4]]}}}