{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:12:58Z","timestamp":1779383578628,"version":"3.53.1"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8461323","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"3071-3075","source":"Crossref","is-referenced-by-count":14,"title":["3D Mouth Tracking from a Compact Microphone Array Co-Located with a camera"],"prefix":"10.1109","author":[{"given":"Xinyuan","family":"Qian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessio","family":"Xompero","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Cavallaro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessio","family":"Brutti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oswald","family":"Lanz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maurizio","family":"Omologo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2010.06.005"},{"key":"ref11","first-page":"1","article-title":"Three dimensional object tracking based on audiovisual fusion using particle swarm optimization","author":"keyrouz","year":"2008","journal-title":"The 5th international conference on information fusion"},{"key":"ref12","first-page":"2270","article-title":"Probabilistic approach for building auditory maps with a mobile microphone array","author":"kallakuri","year":"2013","journal-title":"Proc of IEEE Int Conf on Robotics and Automation"},{"key":"ref13","first-page":"5201","article-title":"Using sound reflections to detect moving entities out of the field of view","author":"kallakuri","year":"2013","journal-title":"Proc of IEEE\/RSJ Int Conf on Intelligent Robots and Systems"},{"key":"ref14","first-page":"677","article-title":"Mapping sound emitting structures in 3d","author":"even","year":"2014","journal-title":"Proc of IEEE Int Conf on Robotics and Automation"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/78.978374"},{"key":"ref16","first-page":"1158","article-title":"Spatiograms versus histograms for region-based tracking","author":"birchfield","year":"2005","journal-title":"Proc of Int Conf on Computer Vision and Pattern Recognition"},{"key":"ref17","first-page":"1069","article-title":"An improved spatiogram similarity measure for robust object localisation","author":"conaire","year":"2007","journal-title":"Proc of IEEE Int Conf on Audio Speech and Signal Processing"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1155\/2010\/147495"},{"key":"ref19","first-page":"273","article-title":"Acoustic event localization using a crosspower-spectrum phase based technique","author":"omologo","year":"1994","journal-title":"Proc of IEEE Int Conf on Audio Speech and Signal Processing"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1007\/978-3-319-22482-4_17","article-title":"Audio-visual speech-turn detection and tracking","author":"gebru","year":"2015","journal-title":"International Conference on Latent Variable Analysis and Signal Separation"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2377515"},{"key":"ref6","first-page":"1154","article-title":"Joint audio-visual tracking using particle filters","volume":"2002","author":"zotkin","year":"2002","journal-title":"EURASIP J on Applied Signal Processing"},{"key":"ref5","first-page":"1","article-title":"Person tracking via audio and video fusion","author":"d\u2019arca","year":"2012","journal-title":"Data Fusion & Target Tracking Conf Alg & App"},{"key":"ref8","first-page":"55","article-title":"A generative approach to audio-visual person tracking","author":"brunelli","year":"2006","journal-title":"Classification of Events Activities and Relationships Evaluation and Workshop"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1088463.1088477"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2008.2001429"},{"key":"ref9","first-page":"974","article-title":"A joint particle filter to track the position and head orientation of people using audio visual cues","author":"brutti","year":"2010","journal-title":"Proc of European Signal Processing Conference"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2003.1206512"},{"key":"ref20","first-page":"320","volume":"24","author":"knapp","year":"1976","journal-title":"The generalized correlation method for estimation of time delay"},{"key":"ref22","first-page":"2896","article-title":"3D audio-visual speaker tracking with an adaptive particle filter","author":"qian","year":"2017","journal-title":"Proc of IEEE Int Conf on Audio Speech and Signal Processing"},{"key":"ref21","first-page":"1","article-title":"Acoustic transduction","author":"omologo","year":"1998","journal-title":"Spoken Dialogue with Computers"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.177"},{"key":"ref23","first-page":"182","article-title":"AV16.3: an audio-visual corpus for speaker localization and tracking","author":"lathoud","year":"2004","journal-title":"Machine Learning for Multimodal Interaction"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000013087.49260.fb"},{"key":"ref25","author":"wu","year":"2015","journal-title":"A lightened CNN for deep face representation"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Calgary, AB","start":{"date-parts":[[2018,4,15]]},"end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08461323.pdf?arnumber=8461323","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T01:07:44Z","timestamp":1598231264000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461323\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8461323","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}