{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:13:16Z","timestamp":1783699996739,"version":"3.55.0"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3067113","type":"journal-article","created":{"date-parts":[[2021,3,18]],"date-time":"2021-03-18T19:56:20Z","timestamp":1616097380000},"page":"1594-1608","source":"Crossref","is-referenced-by-count":37,"title":["Exploiting Temporal Context in CNN Based Multisource DOA Estimation"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1819-0482","authenticated-orcid":false,"given":"Alexander","family":"Bohlender","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9331-222X","authenticated-orcid":false,"given":"Ann","family":"Spriet","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wouter","family":"Tirry","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9131-3309","authenticated-orcid":false,"given":"Nilesh","family":"Madhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"UMA-16 USB microphone array","year":"0"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1121\/1.2799929"},{"key":"ref33","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume":"37","author":"ioffe","year":"0","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref32","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref31","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref30","article-title":"RIR generator","author":"habets","year":"2020"},{"key":"ref37","article-title":"TSP speech database","author":"kabal","year":"0"},{"key":"ref36","first-page":"1509","article-title":"A pitch tracking corpus with evaluation on multipitch tracking scenario","author":"pirker","year":"0","journal-title":"Proc 12th Annu Conf Int Speech Commun Assoc"},{"key":"ref35","article-title":"TIMIT acoustic-phonetic continuous speech corpus LDC93S1","author":"garofolo","year":"0"},{"key":"ref34","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"0","journal-title":"Proc 27th Int Conf Int Conf Mach Learn Ser"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053359"},{"key":"ref40","article-title":"Speech processing, transmission and quality aspects (STQ); speech quality performance in the presence of background noise; part 1: Background noise simulation technique and background noise database","year":"2008"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2005.850882"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1121\/1.4883360"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1121\/1.4929941"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471660"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2337846"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953333"},{"key":"ref17","first-page":"178","article-title":"Robust speaker localization guided by deep learning-based time-frequency masking","volume":"27","author":"wang","year":"2019","journal-title":"IEEE Transactions on Audio"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178484"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682574"},{"key":"ref28","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2010.04.003"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2911401"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162830"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAP.1986.1143830"},{"key":"ref29","first-page":"125","article-title":"Wavenet: A. generative model for raw audio","author":"van den oord","year":"0","journal-title":"Proc 9th ISCA Speech Synth Workshop"},{"key":"ref5","article-title":"A high-accuracy, low-latency technique for talker localization in reverberant environments using microphone arrays","author":"dibiase","year":"2000"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471693"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/29.32276"},{"key":"ref2","first-page":"i?529","article-title":"On the approximate W-disjoint orthogonality of speech","volume":"1","author":"rickard","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8902551"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/9780470727188.ch6"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553182"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2901664"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170010"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461386"},{"key":"ref41","article-title":"Acoustics - application of new measurement methods in building and room acoustics","year":"2006"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref26","first-page":"165","article-title":"A dataset of reverberant spatial sound scenes with moving sources for sound event localization and detection","author":"politis","year":"0","journal-title":"Proc Workshop Detection Classification Acoust Scenes Events"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.33682\/9f2t-ab23"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09381644.pdf?arnumber=9381644","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:57Z","timestamp":1652194437000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9381644\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3067113","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}