{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T06:12:05Z","timestamp":1773295925789,"version":"3.50.1"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2018,2,1]],"date-time":"2018-02-01T00:00:00Z","timestamp":1517443200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["637422"],"award-info":[{"award-number":["637422"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"name":"U.K. RAEng Research Fellowship","award":["RF\/128"],"award-info":[{"award-number":["RF\/128"]}]},{"DOI":"10.13039\/501100000266","name":"U.K. Engineering and Physical Sciences Research Council","doi-asserted-by":"crossref","award":["EP\/N014111\/1"],"award-info":[{"award-number":["EP\/N014111\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2018,2]]},"DOI":"10.1109\/taslp.2017.2778423","type":"journal-article","created":{"date-parts":[[2017,11,30]],"date-time":"2017-11-30T19:40:53Z","timestamp":1512070853000},"page":"379-393","source":"Crossref","is-referenced-by-count":219,"title":["Detection and Classification of Acoustic Scenes and Events: Outcome of the DCASE 2016 Challenge"],"prefix":"10.1109","volume":"26","author":[{"given":"Annamaria","family":"Mesaros","sequence":"first","affiliation":[]},{"given":"Toni","family":"Heittola","sequence":"additional","affiliation":[]},{"given":"Emmanouil","family":"Benetos","sequence":"additional","affiliation":[]},{"given":"Peter","family":"Foster","sequence":"additional","affiliation":[]},{"given":"Mathieu","family":"Lagrange","sequence":"additional","affiliation":[]},{"given":"Tuomas","family":"Virtanen","sequence":"additional","affiliation":[]},{"given":"Mark D.","family":"Plumbley","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Music Information Retrieval Evaluation eXchange (MIREX).","year":"2017"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964310"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2015.7336899"},{"key":"ref31","first-page":"80","article-title":"An open dataset for research on audio field recording archives: Freefield1010","author":"stowell","year":"0","journal-title":"Proc Int AES Conf Semantic Audio"},{"key":"ref30","first-page":"1","article-title":"Automatic recognition of urban sound sources","author":"defr\u00e9ville","year":"0","journal-title":"Proc Convention Audio Engineering Society"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952264"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690563"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.488"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2012.10.004"},{"key":"ref62","article-title":"Discriminative training of GMM parameters for audio scene classification","author":"yun","year":"2016"},{"key":"ref61","author":"murphy","year":"2012","journal-title":"Machine Learning A Probabilistic Perspective"},{"key":"ref63","article-title":"CQT-based convolutional neural networks for audio scene classification and domestic audio tagging","author":"lidy","year":"2016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2279318"},{"key":"ref64","author":"conover","year":"1980","journal-title":"Practical Nonparametric Statistics"},{"key":"ref27","first-page":"547","article-title":"Multivariate autoregressive mixture models for music auto-tagging","author":"coviello","year":"0","journal-title":"Proc Int Conf Music Inf Retrieval"},{"key":"ref29","first-page":"220","article-title":"Sample-level deep convolutional neural networks for music auto-tagging using raw waveforms","author":"lee","year":"0","journal-title":"Proc 14th Int Conf Sound and Music Computing Conf (SMC)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1250\/ast.29.247"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2003.1318488"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690575"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178320"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.913750"},{"key":"ref23","first-page":"385","article-title":"Automatic generation of social tags for music recommendation","author":"eck","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","first-page":"492","article-title":"Sparse multi-label linear embedding nonnegative tensor factorization for automatic music tagging","author":"panagakis","year":"0","journal-title":"Proc 18th Eur Signal Process Conf"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1743384.1743400"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2587218"},{"key":"ref51","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1038\/44565","article-title":"Learning the parts of objects by non-negative matrix factorization","volume":"401","author":"li","year":"1999","journal-title":"Nature"},{"key":"ref59","first-page":"1918","article-title":"The CHiME corpus: A resource and a challenge for computational hearing in multisource environments","author":"christensen","year":"0","journal-title":"Proc 11th INTERSPEECH Conf"},{"key":"ref58","article-title":"Detection and classification of acoustic scenes and events DCASE2016","author":"mesaros","year":"2016"},{"key":"ref57","first-page":"6","article-title":"Sound event detection in multichannel audio using spatial and harmonic features","author":"adavanne","year":"0","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2016 Workshop (DCASE2016)"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8169985"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1001\/archpsyc.61.3.310"},{"key":"ref54","first-page":"45","article-title":"Acoustic event detection method using semi-supervised non-negative matrix factorization with mixtures of local dictionaries","author":"komatsu","year":"0","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2016 Workshop (DCASE2016)"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref52","article-title":"A Matlab toolbox for efficient perfect reconstruction time-frequency transforms with log-frequency resolution","author":"sch\u00f6rkhuber","year":"0","journal-title":"AES 53rd Conference on Semantic Audio"},{"key":"ref10","first-page":"1272","article-title":"Audio context recognition using audio event histograms","author":"heittola","year":"0","journal-title":"Proc 18th Eur Signal Process Conf"},{"key":"ref11","first-page":"142","article-title":"Histogram of gradients of time-frequency representations for audio scene classification","volume":"23","author":"rakotomamonjy","year":"2015","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref12","first-page":"95","article-title":"DCASE 2016 acoustic scene classification using convolutional neural networks","author":"valenti","year":"0","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2016 Workshop (DCASE2016)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref14","first-page":"1267","article-title":"Acoustic event detection in real-life recordings","author":"mesaros","year":"0","journal-title":"Proc 18th Eur Signal Process Conf"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.camwa.2012.03.077"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701847"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177950"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-015-0069-2"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178031"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_45"},{"key":"ref3","first-page":"187","article-title":"TRECVid semantic indexing of video: A 6-year retrospective","volume":"4","author":"awad","year":"2016","journal-title":"ITE Trans on Media Tech and App"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2016.7738875"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-016-0306-6"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.854103"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2326181"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170047"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1121\/1.2750160"},{"key":"ref46","article-title":"Empirical study on ensemble method of deep neural networks for acoustic scene classification","author":"kim","year":"2016"},{"key":"ref45","article-title":"Supervised nonnegative matrix factorization for acoustic scene classification","author":"bisot","year":"2016"},{"key":"ref48","article-title":"Tone-fit and MFCC scene classification compared to human recognition.","author":"krijnders","year":"0"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/BF02295996"},{"key":"ref42","first-page":"65","article-title":"Pairwise decomposition with deep neural networks and multiscale kernel subspace learning for acoustic scene classification","author":"marchi","year":"0","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2016 Workshop (DCASE2016)"},{"key":"ref41","article-title":"CP-JKU submissions for DCASE-2016: A hybrid approach using binaural i-vectors and deep convolutional neural networks","author":"eghbal-zadeh","year":"2016"},{"key":"ref44","first-page":"11","article-title":"Acoustic scene classification using parallel combination of LSTM and CNN","author":"bae","year":"0","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2016 Workshop (DCASE2016)"},{"key":"ref43","article-title":"Score fusion of classification systems for acoustic scene classification","author":"park","year":"2016"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8186325\/08123864.pdf?arnumber=8123864","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:24:17Z","timestamp":1642004657000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8123864\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2]]},"references-count":64,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2017.2778423","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,2]]}}}