{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T02:12:23Z","timestamp":1773108743406,"version":"3.50.1"},"reference-count":42,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,24]]},"DOI":"10.23919\/eusipco47968.2020.9287716","type":"proceedings-article","created":{"date-parts":[[2020,12,18]],"date-time":"2020-12-18T16:54:18Z","timestamp":1608310458000},"page":"16-20","source":"Crossref","is-referenced-by-count":58,"title":["SELD-TCN: Sound Event Localization & Detection via Temporal Convolutional Networks"],"prefix":"10.23919","author":[{"given":"Karim","family":"Guirguis","sequence":"first","affiliation":[]},{"given":"Christoph","family":"Schorn","sequence":"additional","affiliation":[]},{"given":"Andre","family":"Guntoro","sequence":"additional","affiliation":[]},{"given":"Sherif","family":"Abdulatif","sequence":"additional","affiliation":[]},{"given":"Bin","family":"Yang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"TUT Sound Events 2018 - Ambisonic, Reverberant and Real-life Impulse Response Dataset","author":"adavanne","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"ref33","article-title":"WaveNet A Generative Model for Raw Audio","author":"van den oord","year":"2016"},{"key":"ref32","article-title":"Recent Advances in Convolutional Neural Networks","author":"gu","year":"2015","journal-title":"Pattern Recognition"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2017.8050816"},{"key":"ref30","first-page":"9","article-title":"Recurrent Neural Networks Hardware Implementation on FPGA","author":"chang","year":"2016"},{"key":"ref37","article-title":"A Wavenet for Speech Denoising","author":"rethage","year":"2017"},{"key":"ref36","article-title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","author":"ioffe","year":"2015"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.33682\/xb0q-a335"},{"key":"ref34","article-title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","author":"bai","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170010"},{"key":"ref40","article-title":"Direction of Arrival Estimation for Multiple Sound Sources Using Convolutional Recurrent Neural Network","author":"adavanne","year":"2017"},{"key":"ref11","article-title":"Direction of Arrival Estimation for Multiple Sound Sources Using Convolutional Recurrent Neural Network","author":"adavanne","year":"2017"},{"key":"ref12","article-title":"Acoustic event detection using signal enhancement and spectro-temporal feature extraction","author":"schr\u00f6der","year":"2013","journal-title":"Proc IEEE AASP Challenge Detection and Classification of Acoustic Scenes and Events"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2013-1"},{"key":"ref14","article-title":"Sound Event Detection in Multisource Environments Using Source Separation","author":"heittola","year":"2011"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.camwa.2012.03.077"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-30232-9_14"},{"key":"ref17","article-title":"Acoustic Event Detection Method Using Semi-Supervised Non-Negative Matrix Factorization with Mixtures of Local Dictionaries","author":"komatsu","year":"2016"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178031"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-123"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683064"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/11925293_26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489470"},{"key":"ref3","first-page":"327","article-title":"Musical Instrument Recognition in Polyphonic Audio Using Source-Filter Model for Sound Separation","author":"heittola","year":"2009"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178484"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682909"},{"key":"ref5","article-title":"On sound source localization of speech signals using deep neural networks","author":"roden","year":"2015"},{"key":"ref8","author":"nugraha","year":"2017","journal-title":"Deep Neural Network Based Multichannel Audio Source Separation"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846325"},{"key":"ref2","article-title":"An Efficient Temporally-Constrained Probabilistic Model for Multiple-Instrument Music Transcription","author":"benetos","year":"2015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2016.7738817"},{"key":"ref1","article-title":"Estimating animal population density using passive acoustics","volume":"88","author":"marques","year":"2012","journal-title":"Biological Reviews of the Cambridge Philosophical Society"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.23919\/FRUCT.2019.8711906"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2740002"},{"key":"ref21","article-title":"Sound Event Detection in Multichannel Audio Using Spatial and Harmonic Features","author":"adavanne","year":"2016"},{"key":"ref42","article-title":"Adam: A Method for Stochastic Optimization","author":"kingma","year":"2014","journal-title":"International Conference on Learning Representations"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690575"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1121\/1.4806631"},{"key":"ref23","first-page":"493","article-title":"Virtual Adversarial Training and Data Augmentation for Acoustic Event Detection with Gated Recurrent Neural Networks","author":"z\u00f6hrer","year":"2017"},{"key":"ref26","article-title":"Multichannel Sound Event Detection Using 3D Convolutional Neural Networks for Learning Interchannel Features","author":"adavanne","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952260"}],"event":{"name":"2020 28th European Signal Processing Conference (EUSIPCO)","location":"Amsterdam, Netherlands","start":{"date-parts":[[2021,1,18]]},"end":{"date-parts":[[2021,1,21]]}},"container-title":["2020 28th European Signal Processing Conference (EUSIPCO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9287308\/9287310\/09287716.pdf?arnumber=9287716","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,22]],"date-time":"2021-02-22T22:15:40Z","timestamp":1614032140000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9287716\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,24]]},"references-count":42,"URL":"https:\/\/doi.org\/10.23919\/eusipco47968.2020.9287716","relation":{},"subject":[],"published":{"date-parts":[[2021,1,24]]}}}