{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T23:10:03Z","timestamp":1748646603836,"version":"3.41.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319249469"},{"type":"electronic","value":"9783319249476"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/2.5"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-24947-6_12","type":"book-chapter","created":{"date-parts":[[2015,10,6]],"date-time":"2015-10-06T18:10:30Z","timestamp":1444155030000},"page":"142-153","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Temporal Acoustic Words for Online Acoustic Event Detection"],"prefix":"10.1007","author":[{"given":"Rene","family":"Grzeszick","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Axel","family":"Plinge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gernot A.","family":"Fink","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,11,3]]},"reference":[{"issue":"2","key":"12_CR1","doi-asserted-by":"publisher","first-page":"881","DOI":"10.1121\/1.2750160","volume":"122","author":"JJ Aucouturier","year":"2007","unstructured":"Aucouturier, J.J., Defreville, B., Pachet, F.: The Bag-of-Frames Approach to Audio Pattern Recognition: A Sufficient Model for Urban Soundscapes but Not for Polyphonic Music. J. Acoust. Soc. Am. 122(2), 881\u2013891 (2007)","journal-title":"J. Acoust. Soc. Am."},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Carletti, V., Foggia, P., Percannella, G., Saggese, A., Strisciuglio, N., Vento, M.: Audio Surveillance using a Bag of Aural Words Classifier. In: 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. 81\u201386. IEEE (2013)","DOI":"10.1109\/AVSS.2013.6636620"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Chatfield, K., Lempitsky, V., Vedaldi, A., Zisserman, A.: The devil is in the details: an evaluation of recent feature encoding methods. In: Proceeding British Machine Vision Conference (BMVC) (2011)","DOI":"10.5244\/C.25.76"},{"key":"12_CR4","series-title":"Advances in Computer Vision and Pattern Recognition","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-6308-4","volume-title":"Markov Models for Pattern Recognition. From Theory to Applications","author":"GA Fink","year":"2014","unstructured":"Fink, G.A.: Markov Models for Pattern Recognition. From Theory to Applications. Advances in Computer Vision and Pattern Recognition, 2nd edn. Springer, London (2014)","edition":"2"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Foggia, P., Saggese, A., Strisciuglio, N., Vento, M.: Cascade classifiers trained on Gammatonegrams for reliably detecting Audio Events. In: 11th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 50\u201355. IEEE (2014)","DOI":"10.1109\/AVSS.2014.6918643"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Giannoulis, D., Benetos, E., Stowell, D., Rossignol, M., Lagrange, M., Plumbley, M.D.: Detection and classification of acoustic scenes and events: an IEEE AASP challenge. In: IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), pp. 1\u20134. IEEE (2013)","DOI":"10.1109\/WASPAA.2013.6701819"},{"key":"12_CR7","series-title":"Springer Series in Statistics","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-3235-1","volume-title":"Permutation Tests - A Practical Guide to Resampling Methods for Testing Hypotheses","author":"P Good","year":"2000","unstructured":"Good, P.: Permutation Tests - A Practical Guide to Resampling Methods for Testing Hypotheses. Springer Series in Statistics, 2nd edn. Springer, New York (2000)","edition":"2"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Grzeszick, R., Rothacker, L., Fink, G.A.: Bag-of-Features Representations using Spatial Visual Vocabularies for Object Classification. In: Proceeding International Conference on Image Processing (ICIP) (2013)","DOI":"10.1109\/ICIP.2013.6738590"},{"issue":"2","key":"12_CR9","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1007\/s13735-012-0024-2","volume":"2","author":"YG Jiang","year":"2013","unstructured":"Jiang, Y.G., Bhattacharya, S., Chang, S.F., Shah, M.: High-level event recognition in unconstrained videos. Int. J. Multimedia Inf. Retrieval 2(2), 73\u2013101 (2013)","journal-title":"Int. J. Multimedia Inf. Retrieval"},{"key":"12_CR10","unstructured":"Klinck, H., Stelzer, K., Jafarmadar, K., Mellinger, D.K.: AAS Endurance: An Autonomous Acoustic Sailboat for Marine Mammal Research. In: International Robotic Sailing Conference (2009)"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: Proceeding IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, pp. 2169\u20132178 (2006)","DOI":"10.1109\/CVPR.2006.68"},{"key":"12_CR12","unstructured":"Nogueira, W., Roma, G., Herrera, P.: Automatic Event Classification using Front End Single Channel Noise Reduction, MFCC Features and a Support Vector Machine Classifier. Technical report, IEEE AASP Challenge: Detection and Classification of Acoustic Scenes and Events (2013). http:\/\/c4dm.eecs.qmul.ac.uk\/sceneseventschallenge\/abstracts\/OL\/NR2.pdf"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Pancoast, S., Akbacak, M.: Bag-of-audio-words approach for multimedia event classification. In: Interspeech, pp. 2105\u20132108 (2012)","DOI":"10.21437\/Interspeech.2012-561"},{"issue":"1","key":"12_CR14","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/TASLP.2014.2367814","volume":"23","author":"H Phan","year":"2014","unstructured":"Phan, H., Maasz, M., Mazur, R., Mertins, A.: Random regression forests for acoustic event detection and classification. IEEE\/ACM Trans. Audio Speech Lang. Process. 23(1), 20\u201331 (2014). http:\/\/ieeexplore.ieee.org\/articleDetails.jsp?arnumber=6949625","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Phan, H., Mertins, A.: Exploiting superframe cooccurence for acoustic event recognition. In: European Signal Processing Conference (2014)","DOI":"10.1109\/EUSIPCO.2015.7362844"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Plinge, A., Grzeszick, R., Fink, G.A.: A bag-of-features approach to acoustic event detection. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (2014)","DOI":"10.1109\/ICASSP.2014.6854293"},{"issue":"16","key":"12_CR17","doi-asserted-by":"publisher","first-page":"2216","DOI":"10.1016\/j.patrec.2012.07.019","volume":"33","author":"J S\u00e1nchez","year":"2012","unstructured":"S\u00e1nchez, J., Perronnin, F., De Campos, T.: Modeling the spatial layout of images beyond spatial pyramids. Pattern Recogn. Lett. 33(16), 2216\u20132223 (2012)","journal-title":"Pattern Recogn. Lett."},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Schr\u00f6der, J., Cauchi, B., Sch\u00e4dler, M.R., Moritz, N., Adiloglu, K., Anem\u00fcller, J., Doclo, S., Kollmeier, B., Goetze, S.: Acoustic event detection using signal enhancement and spectro-temporal feature extraction. Technical report, IEEE AASP Challenge: Detection and Classification of Acoustic Scenes and Events (2013). http:\/\/c4dm.eecs.qmul.ac.uk\/sceneseventschallenge\/abstracts\/OL\/SCS.pdf","DOI":"10.1109\/WASPAA.2013.6701868"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Shao, Y., Srinivasan, S., Wang, D.: Incorporating auditory feature uncertainties in robust speaker identification. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 277\u2013280 (2007)","DOI":"10.1109\/ICASSP.2007.366903"},{"issue":"10","key":"12_CR20","doi-asserted-by":"publisher","first-page":"1692","DOI":"10.1109\/JPROC.2010.2057231","volume":"98","author":"ST Shivappa","year":"2010","unstructured":"Shivappa, S.T., Trivedi, M.M., Rao, B.D.: Audiovisual information fusion in human computer interfaces and intelligent environments: a survey. Proc. IEEE 98(10), 1692\u20131715 (2010)","journal-title":"Proc. IEEE"},{"key":"12_CR21","unstructured":"Steele, D., Krijnders, J.D., Guastavino, C.: The Sensor City Initiative: Cognitive Sensors for Soundscape Transformations. GIS Ostrava (2013)"},{"issue":"5","key":"12_CR22","doi-asserted-by":"publisher","first-page":"959","DOI":"10.1109\/TPAMI.2011.174","volume":"34","author":"H Tang","year":"2012","unstructured":"Tang, H., Chu, S.M., Hasegawa-Johnson, M., Huang, T.S.: Partially supervised speaker clustering. IEEE Trans. Pattern Anal. Mach. Intell. 34(5), 959\u2013971 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"12_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1007\/978-3-540-69568-4_29","volume-title":"Multimodal Technologies for Perception of Humans","author":"A Temko","year":"2007","unstructured":"Temko, A., Malkin, R.G., Zieger, C., Macho, D., Nadeu, C., Omologo, M.: CLEAR evaluation of acoustic event detection and classification systems. In: Stiefelhagen, R., Garofolo, J.S. (eds.) CLEAR 2006. LNCS, vol. 4122, pp. 311\u2013322. Springer, Heidelberg (2007)"},{"key":"12_CR24","unstructured":"Vuegen, L., Broeck, B.V.D., Karsmakers, P., Gemmeke, J.F., Vanrumste, B., Hamme, H.V.: An MFCC-GMM approach for event detection and classification. Technical report, IEEE AASP Challenge: Detection and Classification of Acoustic Scenes and Events (2013). http:\/\/c4dm.eecs.qmul.ac.uk\/sceneseventschallenge\/abstracts\/OL\/VVK.pdf"},{"key":"12_CR25","unstructured":"Wang, D., Brown, G.J. (eds.): Computational Auditory Scene Analysis: Principles, Algorithms, and Applications. IEEE Press (2006)"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Young, S.H., Scanlon, M.V.: Robotic vehicle uses acoustic array for detection and localization in Urban environments. in: SPIE Proceeding Mobile Robot Perception, vol. 4364, pp. 264\u2013273 (2001)","DOI":"10.1117\/12.439985"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Zeppelzauer, M., St\u00f6ger, A.S., Breiteneder, C.: Acoustic detection of elephant presence in noisy environments. In: Proceedings of the 2nd ACM international workshop on Multimedia analysis for ecological data, pp. 3\u20138. ACM (2013)","DOI":"10.1145\/2509896.2509900"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-24947-6_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T22:50:42Z","timestamp":1748645442000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-24947-6_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319249469","9783319249476"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-24947-6_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"3 November 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}