{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T12:48:54Z","timestamp":1753274934007,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095472","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Improved Deep Speaker Localization and Tracking: Revised Training Paradigm and Controlled Latency"],"prefix":"10.1109","author":[{"given":"Alexander","family":"Bohlender","sequence":"first","affiliation":[{"name":"Ghent University - Imec,IDLab,Department of Electronics and Information Systems,Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liesbeth","family":"Roelens","sequence":"additional","affiliation":[{"name":"Ghent University - Imec,IDLab,Department of Electronics and Information Systems,Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nilesh","family":"Madhu","sequence":"additional","affiliation":[{"name":"Ghent University - Imec,IDLab,Department of Electronics and Information Systems,Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"TIMIT Acoustic-Phonetic Continuous Speech Corpus LDC93S1","author":"garofolo","year":"1993","journal-title":"Linguistic Data Consortium"},{"key":"ref12","first-page":"5755","article-title":"Highway long short-term memory RNNs for distant speech recognition","author":"zhang","year":"2016","journal-title":"Proc IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"article-title":"RIR generator","year":"2023","author":"habets","key":"ref15"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-317"},{"key":"ref20","first-page":"4841","article-title":"Leastsquares DOA estimation with an informed phase unwrapping and full bandwidth robustness","author":"bohlender","year":"2020","journal-title":"Proc IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref11","article-title":"A high-accuracy, low-latency technique for talker localization in reverberant environments using microphone arrays","author":"dibiase","year":"2000","journal-title":"Ph D thesis"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2901664"},{"journal-title":"ETSI EG 202 396-1","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":"2005","key":"ref21"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616138"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639593"},{"key":"ref17","first-page":"1","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"Proc International Conference on Learning Representations (ICLR)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1121\/1.2799929"},{"year":"0","key":"ref19","article-title":"UMA-16 USB microphone array"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1109\/TAU.1969.1162058","article-title":"IEEE recommended practice for speech quality measurements","volume":"17","author":"rothauser","year":"1969","journal-title":"IEEE Transactions on Audio and Electroacoustics"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3040031"},{"key":"ref7","first-page":"165","article-title":"A dataset of reverberant spatial sound scenes with moving sources for sound event localization and detection","author":"politis","year":"2020","journal-title":"Proc Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3067113"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1121\/10.0011809"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/9780470727188.ch6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.33682\/xb0q-a335"},{"key":"ref5","first-page":"4160","article-title":"SoundDet: Polyphonic moving sound event detection and localization from raw waveform","author":"he","year":"2021","journal-title":"Proc of the International Conference on Machine Learning (ICML)"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095472.pdf?arnumber=10095472","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:00:38Z","timestamp":1699902038000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095472\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095472","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}