{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T12:45:46Z","timestamp":1763642746629,"version":"3.44.0"},"reference-count":68,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"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":[[2019,9]]},"DOI":"10.1109\/mmsp.2019.8901720","type":"proceedings-article","created":{"date-parts":[[2019,11,25]],"date-time":"2019-11-25T14:13:05Z","timestamp":1574691185000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Selective Hearing: A Machine Listening Perspective"],"prefix":"10.1109","author":[{"given":"Estefan\u00eda","family":"Cano","sequence":"first","affiliation":[{"name":"Semantic Music Technologies, Fraunhofer IDMT,Ilmenau,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanna","family":"Lukashevich","sequence":"additional","affiliation":[{"name":"Semantic Music Technologies, Fraunhofer IDMT,Ilmenau,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952211"},{"key":"ref38","first-page":"321","article-title":"Zero mean convolutions for level-invariant singing voice detection","author":"schl\u00fctter","year":"2018","journal-title":"Proceedings of the 19th International Society for Music Information Retrieval Conference"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.21437\/Odyssey.2018-46","article-title":"How to train your speaker embeddings extractor","author":"mclaren","year":"2018","journal-title":"Odyssey"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178885"},{"key":"ref30","article-title":"Feature learning with raw-waveform CLDNNs for voice activity detection","author":"zazo-candil","year":"0","journal-title":"Proc of Interspeech"},{"key":"ref37","first-page":"569","article-title":"Instrument activity detection in polyphonic music using deep neural networks","author":"gururani","year":"2018","journal-title":"Proceedings of the 19th International Society for Music Information Retrieval Conference"},{"key":"ref36","first-page":"612","article-title":"Deep convolutional networks on the pitch spiral for musical instrument recognition","author":"lonstanlen","year":"2016","journal-title":"Proceedings of the 17th International Society for Music Information Retrieval Conference"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2632307"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1159"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref62","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1007\/978-3-319-22482-4_11","article-title":"Speech enhancement with LSTM recurrent neural networks and its application to noise-robust ASR","author":"weninger","year":"2015","journal-title":"Latent Variable Analysis and Signal Separation"},{"key":"ref61","first-page":"3642","article-title":"SEGAN: speech enhancement generative adversarial network","author":"pascual","year":"0","journal-title":"Proc of Interspeech"},{"key":"ref63","article-title":"Perceptual evaluation of source separation for remixing music","author":"wierstorf","year":"0","journal-title":"Proc Convention Audio Engineering Society"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1151"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1121\/1.4971424"},{"key":"ref27","first-page":"1","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":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462448"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682572"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637694"},{"key":"ref67","first-page":"138","article-title":"Unsupervised adversarial domain adaptation for acoustic scene classification","author":"gharib","year":"0","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events Workshop (DCASE)"},{"key":"ref68","article-title":"A multi-device dataset for urban acoustic scene classification","author":"mesaros","year":"2018","journal-title":"Detection and Classification of Acoustic Scenes and Events"},{"key":"ref2","article-title":"Plausible augmentation of auditory scenes using dynamic binaural synthesis for personalized auditory realities","author":"brandenburg","year":"0","journal-title":"Proc of AES International Conference on Audio for Virtual and Augmented Reality"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2369191"},{"key":"ref20","article-title":"Mean teacher convolution system for dcase 2018 task 4","author":"jiakai","year":"2018","journal-title":"DCASE 2018 Challenge"},{"key":"ref22","first-page":"1","article-title":"End-to-end polyphonic sound event detection using convolutional recurrent neural networks with learned time-frequency representation input","author":"\u00e7akir","year":"0","journal-title":"Proc of International Joint Conference on Neural Networks (IJCNN)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2292894"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461975"},{"key":"ref26","article-title":"Training general-purpose audio tagging networks with noisy labels and iterative self-verification","author":"dorfer","year":"2018","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2018 Workshop (DCASE2018)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683158"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2016.7602895"},{"key":"ref59","article-title":"Speech enhancement based on deep denoising autoencoder","author":"lu","year":"0","journal-title":"Proc of Interspeech"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2795756"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2017.03.017"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2016.2601942"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952158"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2158801"},{"key":"ref53","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1007\/978-3-319-93764-9_28","article-title":"The 2018 signal separation evaluation campaign","author":"stater","year":"2018","journal-title":"Latent Variable Analysis and Signal Separation"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2825440"},{"key":"ref10","first-page":"749","article-title":"New sonorities for early jazz recordings using sound source separation and automatic mixing tools","author":"matz","year":"2015","journal-title":"Proc of the 16th International Society for Music Information Retrieval Conference"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/5.763310"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2901664"},{"key":"ref12","article-title":"Action-sound latency: Are our tools fast enough?","author":"mcpherson","year":"0","journal-title":"Proceedings of the International Conference on New Interfaces for Musical Expression"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2628440"},{"key":"ref14","first-page":"1","article-title":"Signal processing challenges for active noise cancellation headphones","author":"liebich","year":"0","journal-title":"Speech Communication 13 ITG Symposium"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462325"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683810"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2018 Workshop (DCASE 2018) Tampere University of Technology Laboratory of Signal Processing","year":"0","author":"plumbley","key":"ref18"},{"key":"ref19","first-page":"19","article-title":"Large-scale weakly labeled semi-supervised sound event detection in domestic environments","author":"serizel","year":"0","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2018 Workshop (DCASE 2018)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2570945"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2015.03.003"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2647702"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2874719"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2369251"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081613"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952149"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/9781119279860"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2795749"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683732"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8169997"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461639"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2019.01.002"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2740001"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2272524"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2391252"}],"event":{"name":"2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP)","start":{"date-parts":[[2019,9,27]]},"location":"Kuala Lumpur, Malaysia","end":{"date-parts":[[2019,9,29]]}},"container-title":["2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8891847\/8901684\/08901720.pdf?arnumber=8901720","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:41:18Z","timestamp":1755909678000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8901720\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/mmsp.2019.8901720","relation":{},"subject":[],"published":{"date-parts":[[2019,9]]}}}