{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T12:28:43Z","timestamp":1777984123513,"version":"3.51.4"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001807","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","doi-asserted-by":"publisher","award":["2017\/08120-6"],"award-info":[{"award-number":["2017\/08120-6"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001807","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","doi-asserted-by":"publisher","award":["2019\/22945-3"],"award-info":[{"award-number":["2019\/22945-3"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010654","name":"Universidad San Francisco de Quito","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010654","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Poli-Grants Program","award":["17993"],"award-info":[{"award-number":["17993"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3284525","type":"journal-article","created":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T13:27:13Z","timestamp":1686317233000},"page":"2314-2324","source":"Crossref","is-referenced-by-count":23,"title":["Sound Events Localization and Detection Using Bio-Inspired Gammatone Filters and Temporal Convolutional Neural Networks"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8118-4213","authenticated-orcid":false,"given":"Karen Gissell Rosero","family":"Jacome","sequence":"first","affiliation":[{"name":"School of Electrical and Computer Engineering, University of Campinas, Campinas, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6162-3429","authenticated-orcid":false,"given":"Felipe Leonel","family":"Grijalva","sequence":"additional","affiliation":[{"name":"Colegio de Ciencias e Ingenierías “El Politécnico”, Universidad San Francisco de Quito, Quito, Ecuador"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2246-4450","authenticated-orcid":false,"given":"Bruno Sanches","family":"Masiero","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, University of Campinas, Campinas, Brazil"}]}],"member":"263","reference":[{"key":"ref13","first-page":"6","article-title":"Classification of spatial audio location and content using convolutional neural networks","author":"hirvonen","year":"0","journal-title":"Proc Audio Eng Soc 138th Conv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-019-10116-7"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553182"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","first-page":"125","article-title":"A dataset of dynamic reverberant sound scenes with directional interferers for sound event localization and detection","author":"politis","year":"0","journal-title":"Proc Detection Classication Acoustic Scenes Events"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937220"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref36","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref31","article-title":"Sound event localization and detection using FOA domain spatial augmentation","author":"mazzon","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11741-011-0684-2"},{"key":"ref33","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":"10.1121\/1.4883360"},{"key":"ref32","article-title":"A combination of various neural networks for sound event localization and detection","author":"rho","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICICS.2011.6173618"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/B0-08-043076-7\/03501-4"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-04619-7_8"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/Eusipco47968.2020.9287716"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413609"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1121\/1.4981118"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-597"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP52302.2021.9596248"},{"key":"ref24","first-page":"53","author":"roginska","year":"2018","journal-title":"Immersive Sound The Art and Science of Binaural and Multi-Channel Audio"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICSPCC.2017.8242450"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2778423"},{"key":"ref42","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-11455-1"},{"key":"ref41","first-page":"1","article-title":"What is “proximity,” how do early reflections and reverberation affect it, and can it be studied with LOC and existing binaural data?","author":"griesinger","year":"0","journal-title":"Proc 22nd Int Congr Acoust"},{"key":"ref44","article-title":"DCASE 2021 task 3: Spectrotemporally-aligned features for polyphonic sound event localization and detection","author":"nguyen","year":"2021"},{"key":"ref22","first-page":"150","article-title":"Listen carefully and tell: An audio captioning system based on residual learning and Gammatone audio representation","author":"perez-castanos","year":"0","journal-title":"Proc Workshop Detection Classification Acoust Scenes Events"},{"key":"ref43","article-title":"Ensemble of ACCDOA-and EINV2-based systems with D3Nets and impulse response simulation for sound event localization and detection","author":"shimada","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-617"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref29","article-title":"The nigens general sound events database","author":"trowitzsch","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1121\/1.4820885"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/89.966097"},{"key":"ref9","article-title":"Enhancements to the generalized sidelobe canceller for audio beamforming in an immersive environment","author":"townsend","year":"2009"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2008.4711269"},{"key":"ref3","article-title":"Real-time detection of important sounds with a wearable vibration based device for hearing-impaired people","volume":"7","author":"ya?ano?lu","year":"2018","journal-title":"Electronics"},{"key":"ref6","article-title":"Passive acoustic monitoring in ecology and conservation","author":"browning","year":"2017"},{"key":"ref5","first-page":"1859","article-title":"Acoustic source localization and discrimination in urban environments","author":"kushwaha","year":"0","journal-title":"Proc IEEE Int Conf Inf Fusion"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2236316"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10147311.pdf?arnumber=10147311","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T15:43:46Z","timestamp":1704815026000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10147311\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3284525","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.21155257.v1","asserted-by":"object"},{"id-type":"doi","id":"10.36227\/techrxiv.21155257","asserted-by":"object"}]},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}