{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T11:06:49Z","timestamp":1782385609228,"version":"3.54.5"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2017,9,2]],"date-time":"2017-09-02T00:00:00Z","timestamp":1504310400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Key Support Projects of Shanghai Science and Technology Committee","award":["16010500100"],"award-info":[{"award-number":["16010500100"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61402277"],"award-info":[{"award-number":["61402277"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Innovation Program of Shanghai Municipal Education Commission","award":["15ZZ044"],"award-info":[{"award-number":["15ZZ044"]}]},{"name":"National Natural Science Foundation of China","award":["61571279"],"award-info":[{"award-number":["61571279"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2018,2]]},"DOI":"10.1007\/s11042-017-5129-4","type":"journal-article","created":{"date-parts":[[2017,9,1]],"date-time":"2017-09-01T23:46:41Z","timestamp":1504309601000},"page":"3369-3385","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Gaussian filter for TDOA based sound source localization in multimedia surveillance"],"prefix":"10.1007","volume":"77","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1069-4427","authenticated-orcid":false,"given":"Mengyao","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huan","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiukun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihua","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoqiang","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinghua","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2017,9,2]]},"reference":[{"key":"5129_CR1","volume-title":"Microphone Array signal processing","author":"J Benesty","year":"2008","unstructured":"Benesty J, Chen J, Huang Y (2008) Microphone Array signal processing. Springer, Berlin"},{"key":"5129_CR2","first-page":"19","volume-title":"Lecture Notes in Computer Science","author":"Xuehai Bian","year":"2005","unstructured":"Bian X, Abowd GD, Rehg JM (2005) Using sound source localization in a home environment. In: Gellersen HW, Want R, Schmidt A (eds) Pervasive Computing: Third International Conference, PERVASIVE 2005. Proceeding. Springer, Munich, p 19\u201336"},{"key":"5129_CR3","volume-title":"Microphone arrays: signal processing techniques and applications","author":"M Brandstein","year":"2013","unstructured":"Brandstein M, Ward D (2013) Microphone arrays: signal processing techniques and applications. Springer Science and Business Media, Medford"},{"issue":"1","key":"5129_CR4","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1109\/89.554268","volume":"5","author":"MS Brandstein","year":"1997","unstructured":"Brandstein MS, Adcock JE, Silverman HF (1997) A closed-form location estimator for use with room environment microphone arrays. IEEE Trans Speech Audio Process 5(1):45\u201350","journal-title":"IEEE Trans Speech Audio Process"},{"issue":"7","key":"5129_CR5","doi-asserted-by":"publisher","first-page":"953","DOI":"10.1109\/29.1617","volume":"36","author":"KM Buckley","year":"1988","unstructured":"Buckley KM, Griffiths LJ (1988) Broad-band signal-subspace spatial-spectrum (BASS-ALE) estimation. IEEE Trans Acoust Speech Signal Process 36(7):953\u2013964","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"issue":"4","key":"5129_CR6","doi-asserted-by":"publisher","first-page":"922","DOI":"10.1121\/1.381623","volume":"62","author":"GC Carter","year":"1977","unstructured":"Carter GC (1977) Variance bounds for passively locating an acoustic source with a symmetric line array. J Acoust Soc Am 62(4):922\u2013926","journal-title":"J Acoust Soc Am"},{"issue":"10","key":"5129_CR7","doi-asserted-by":"publisher","first-page":"1497","DOI":"10.1109\/PROC.1973.9300","volume":"61","author":"GC Carter","year":"1973","unstructured":"Carter GC, Nuttall AH, Cable PG (1973) The smoothed coherence transform. Proc IEEE 61(10):1497\u20131498","journal-title":"Proc IEEE"},{"issue":"2","key":"5129_CR8","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1109\/89.486067","volume":"4","author":"B Champagne","year":"1996","unstructured":"Champagne B, Bedard S, Stephenne A (1996) Performance of time-delay estimation in the presence of room reverberation. IEEE Trans Speech Audio Process 4(2):148\u2013152","journal-title":"IEEE Trans Speech Audio Process"},{"issue":"7","key":"5129_CR9","doi-asserted-by":"publisher","first-page":"1502","DOI":"10.1109\/TNNLS.2015.2441735","volume":"27","author":"X Chang","year":"2016","unstructured":"Chang X, Nie F, Wang S, Yang Y, Zhou X, Zhang C (2016) Compound rank-k projections for bilinear analysis. IEEE Trans Neural Netw Lear Syst 27(7):1502\u20131513","journal-title":"IEEE Trans Neural Netw Lear Syst"},{"issue":"5","key":"5129_CR10","doi-asserted-by":"publisher","first-page":"1180","DOI":"10.1109\/TCYB.2016.2539546","volume":"47","author":"X Chang","year":"2017","unstructured":"Chang X, Ma Z, Yang Y, Zeng Z, Hauptmann AG (2017) Bi-level semantic representation analysis for multimedia event detection. IEEE Trans Cybernetics 47(5):1180\u20131197","journal-title":"IEEE Trans Cybernetics"},{"issue":"8","key":"5129_CR11","doi-asserted-by":"publisher","first-page":"1617","DOI":"10.1109\/TPAMI.2016.2608901","volume":"39","author":"X Chang","year":"2017","unstructured":"Chang X, Yu YL, Yang Y, Xing EP (2017) Semantic pooling for complex event analysis in untrimmed videos. IEEE Trans Pattern Anal Mach Intell 39(8):1617\u20131632","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"8","key":"5129_CR12","doi-asserted-by":"publisher","first-page":"3911","DOI":"10.1109\/TIP.2017.2708506","volume":"26","author":"X Chang","year":"2017","unstructured":"Chang X, Ma Z, Lin M, Yang Y, Hauptmann A (2017) Feature interaction augmented sparse learning for fast Kinect motion detection. IEEE Trans Image Process 26(8):3911\u20133920","journal-title":"IEEE Trans Image Process"},{"key":"5129_CR13","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1007\/978-3-319-04117-9_5","volume-title":"MultiMedia Modeling","author":"Teck Wee Chua","year":"2014","unstructured":"Chua TW, Leman K, Gao F (2014) Hierarchical audio-visual surveillance for passenger elevators. In: Gurrin C, Hopfgartner F, Hurst W, et al (eds) MultiMedia Modeling: 20th Anniversary International Conference, MMM 2014. Proceedings, Part II. Springer, Dublin, p 44\u201355"},{"issue":"4","key":"5129_CR14","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1145\/2871183","volume":"48","author":"M Crocco","year":"2016","unstructured":"Crocco M, Cristani M, Trucco A, Murino V (2016) Audio surveillance: a systematic review. ACM Comput Surv 48(4):52. \n                    https:\/\/doi.org\/10.1145\/2871183","journal-title":"ACM Comput Surv"},{"issue":"2","key":"5129_CR15","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1109\/TASSP.1985.1164550","volume":"33","author":"Y Ephraim","year":"1985","unstructured":"Ephraim Y, Malah D (1985) Speech enhancement using a minimum mean-square error log-spectral amplitude estimator. IEEE Trans Acoust Speech Signal Process 33(2):443\u2013445","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"key":"5129_CR16","volume-title":"TIMIT acoustic-phonetic continuous speech corpus","author":"JS Garofolo","year":"1993","unstructured":"Garofolo JS, Lamel LF, Fisher WM, Fiscus JG, Pallett DS, Dahlgren NL et al (1993) TIMIT acoustic-phonetic continuous speech corpus. Linguistic Data Consortium, Philadelphia"},{"key":"5129_CR17","doi-asserted-by":"crossref","unstructured":"Guo Y, Hazas M (2010) Acoustic source localization of everyday sounds using wireless sensor networks.\u00a0International conference adjunct papers on ubiquitous computing. ACM, Copenhagen, p 411\u2013412","DOI":"10.1145\/1864431.1864462"},{"issue":"5","key":"5129_CR18","doi-asserted-by":"publisher","first-page":"608","DOI":"10.1109\/TIT.1973.1055077","volume":"19","author":"W Hahn","year":"1973","unstructured":"Hahn W, Tretter S (1973) Optimum processing for delay-vector estimation in passive signal arrays. IEEE Trans Inf Theory 19(5):608\u2013614","journal-title":"IEEE Trans Inf Theory"},{"key":"5129_CR19","first-page":"478","volume":"2","author":"S Haykin","year":"2002","unstructured":"Haykin S (2002) Adaptive filter theory. Prentice Hall 2:478\u2013481","journal-title":"Prentice Hall"},{"issue":"6","key":"5129_CR20","doi-asserted-by":"publisher","first-page":"998","DOI":"10.1109\/TASSP.1982.1163992","volume":"30","author":"JP Ianniello","year":"1982","unstructured":"Ianniello JP (1982) Time delay estimation via cross-correlation in the presence of large estimation errors. IEEE Trans Acoust Speech Signal Process 30(6):998\u20131003","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"key":"5129_CR21","volume-title":"Array signal processing: concepts and techniques","author":"DH Johnson","year":"1992","unstructured":"Johnson DH, Dudgeon DE (1992) Array signal processing: concepts and techniques. P T R Prentice Hall, Upper Saddle River"},{"issue":"4","key":"5129_CR22","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1109\/TASSP.1976.1162830","volume":"24","author":"C Knapp","year":"1976","unstructured":"Knapp C, Carter G (1976) The generalized correlation method for estimation of time delay. IEEE Trans Acoust Speech Signal Process 24(4):320\u2013327","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"key":"5129_CR23","first-page":"107","volume-title":"Communications in Computer and Information Science","author":"J\u00f3zef Kotus","year":"2013","unstructured":"Kotus J, Lopatka K, Czyzewski A, Bogdanis G (2013) Audio-visual surveillance system for application in bank operating room. In: Dziech A, Czy\u017cewski A (eds) Multimedia Communications, Services and Security: 6th International Conference, MCSS 2013. Proceedings. Springer, Krakow, pp 107\u2013120"},{"issue":"1","key":"5129_CR24","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/s11042-012-1183-0","volume":"68","author":"J Kotus","year":"2014","unstructured":"Kotus J, Lopatka K, Czyzewski A (2014) Detection and localization of selected acoustic events in acoustic field for smart surveillance applications. Multimedia Tools and Applications 68(1):5\u201321","journal-title":"Multimedia Tools and Applications"},{"issue":"7","key":"5129_CR25","doi-asserted-by":"publisher","first-page":"1558","DOI":"10.1109\/TMM.2017.2659221","volume":"19","author":"Zhigang Ma","year":"2017","unstructured":"Ma Z, Chang X, Yang Y, Sebe N, Hauptmann A (2017) The many shades of negativity. IEEE Trans Multimedia, PP(99), 1\u20131. doi:\n                    https:\/\/doi.org\/10.1109\/TMM.2017.2659221","journal-title":"IEEE Transactions on Multimedia"},{"key":"5129_CR26","doi-asserted-by":"crossref","unstructured":"Pham QC, Lapeyronnie A, Baudry C, Lucat L (2010) Audio-video surveillance system for public transportation. International conference on image processing theory, tools and applications. IEEE, Paris, p 47\u201353","DOI":"10.1109\/IPTA.2010.5586783"},{"key":"5129_CR27","doi-asserted-by":"publisher","first-page":"821","DOI":"10.1109\/TAES.1972.309614","volume":"6","author":"RO Schmidt","year":"1972","unstructured":"Schmidt RO (1972) A new approach to geometry of range difference location. IEEE Trans Aerosp Electron Syst 6:821\u2013835","journal-title":"IEEE Trans Aerosp Electron Syst"},{"key":"5129_CR28","unstructured":"Schmidt RO (1981) A signal subspace approach to multiple emitter location spectral estimation. Ph.d.thesis Stanford University"},{"key":"5129_CR29","doi-asserted-by":"crossref","unstructured":"de Silva G C, Yamasaki T, Aizawa K (2008) Audio analysis for multimedia retrieval from a ubiquitous home. In: Satoh SI, Nack F, Etoh M (eds) Advances in Multimedia Modeling: International Multimedia Modeling Conference, MMM 2008. Proceedings. Springer, Kyoto, pp 466\u2013476","DOI":"10.1007\/978-3-540-77409-9_44"},{"issue":"12","key":"5129_CR30","doi-asserted-by":"publisher","first-page":"1661","DOI":"10.1109\/TASSP.1987.1165089","volume":"35","author":"JO Smith","year":"1987","unstructured":"Smith JO, Abel JS (1987) Close-form least-squares source location estimation from range-difference measurements. IEEE Trans Acoust Speech Signal Process 35(12):1661\u20131669","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"key":"5129_CR31","doi-asserted-by":"crossref","unstructured":"Stachurski J, Netsch L, Cole R (2013) Sound source localization for video surveillance camera.\u00a0International conference on advanced video and signal based surveillance. IEEE, Krakow, p 93\u201398","DOI":"10.1109\/AVSS.2013.6636622"},{"key":"5129_CR32","doi-asserted-by":"crossref","unstructured":"Svaizer P, Matassoni M, Omologo M (1997) Acoustic source location in a three-dimensional space using crosspower spectrum phase.\u00a0International conference on acoustics, speech, and signal processing. IEEE, Munich, pp 231\u2013234","DOI":"10.1109\/ICASSP.1997.599611"},{"key":"5129_CR33","doi-asserted-by":"crossref","unstructured":"Tan LN, Borgstrom BJ, Alwan A (2010) Voice activity detection using harmonic frequency components in likelihood ratio test.\u00a0International conference on acoustics speech and signal processing. IEEE, Dallas, pp 4466\u20134469","DOI":"10.1109\/ICASSP.2010.5495611"},{"issue":"4","key":"5129_CR34","doi-asserted-by":"publisher","first-page":"823","DOI":"10.1109\/TASSP.1985.1164667","volume":"33","author":"H Wang","year":"1985","unstructured":"Wang H, Kaveh M (1985) Coherent signal-subspace processing for the detection and estimation of angles of arrival of multiple wide-band sources. IEEE Trans Acoust Speech Signal Process 33(4):823\u2013831","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"issue":"5","key":"5129_CR35","doi-asserted-by":"publisher","first-page":"1210","DOI":"10.1109\/TASSP.1983.1164183","volume":"31","author":"M Wax","year":"1983","unstructured":"Wax M, Kailath T (1983) Optimum localization of multiple sources by passive arrays. IEEE Trans Acoust Speech Signal Process 31(5):1210\u20131217","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"issue":"12","key":"5129_CR36","doi-asserted-by":"publisher","first-page":"2494","DOI":"10.1109\/TMM.2016.2602938","volume":"18","author":"Y Yan","year":"2016","unstructured":"Yan Y, Nie F, Li W, Gao C, Yang Y, Xu D (2016) Image classification by cross-media active learning with privileged information. IEEE Trans Multimedia 18(12):2494\u20132502","journal-title":"IEEE Trans Multimedia"},{"issue":"3","key":"5129_CR37","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1109\/TMM.2012.2237023","volume":"15","author":"Y Yang","year":"2013","unstructured":"Yang Y, Ma Z, Hauptmann AG, Sebe N (2013) Feature selection for multimedia analysis by sharing information among multiple tasks. IEEE Trans Multimedia 15(3):661\u2013669","journal-title":"IEEE Trans Multimedia"},{"key":"5129_CR38","unstructured":"Zhu L, Shen J, Liu X, Xie L, Nie L (2016) Learning compact visual representation with canonical views for robust mobile landmark search.\u00a0International joint conference on artificial intelligence. AAAI, New York, pp 3959\u20133965"},{"issue":"99","key":"5129_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tcyb.2016.2591068","volume":"PP","author":"L Zhu","year":"2016","unstructured":"Zhu L, Shen J, Xie L, Cheng Z (2016) Unsupervised topic hypergraph hashing for efficient mobile image retrieval. IEEE Trans Cybernetics PP(99):1\u201314. \n                    https:\/\/doi.org\/10.1109\/tcyb.2016.2591068","journal-title":"IEEE Trans Cybernetics"},{"issue":"2","key":"5129_CR40","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1109\/TKDE.2016.2562624","volume":"29","author":"L Zhu","year":"2017","unstructured":"Zhu L, Shen J, Xie L, Cheng Z (2017) Unsupervised visual hashing with semantic assistant for content-based image retrieval. IEEE Trans Knowl Data Eng 29(2):472\u2013486","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"5129_CR41","doi-asserted-by":"crossref","unstructured":"Zieger C, Brutti A, Svaizer P (2009) Acoustic based surveillance system for intrusion detection.\u00a0\u00a0International conference on advanced video and signal based surveillance. IEEE, Genova, pp 314\u2013319","DOI":"10.1109\/AVSS.2009.49"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-017-5129-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-017-5129-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-017-5129-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,20]],"date-time":"2019-09-20T14:36:42Z","timestamp":1568990202000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-017-5129-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,9,2]]},"references-count":41,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2018,2]]}},"alternative-id":["5129"],"URL":"https:\/\/doi.org\/10.1007\/s11042-017-5129-4","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,9,2]]},"assertion":[{"value":"29 April 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 August 2017","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 August 2017","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 2017","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}