{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:34:53Z","timestamp":1771954493112,"version":"3.50.1"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2018,8,28]],"date-time":"2018-08-28T00:00:00Z","timestamp":1535414400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100004181","name":"Nokia Foundation","doi-asserted-by":"publisher","award":["201510141"],"award-info":[{"award-number":["201510141"]}],"id":[{"id":"10.13039\/501100004181","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Intel Serv Robotics"],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1007\/s11370-018-0258-9","type":"journal-article","created":{"date-parts":[[2018,8,29]],"date-time":"2018-08-29T19:45:10Z","timestamp":1535571910000},"page":"335-346","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Common sounds in bedrooms (CSIBE) corpora for sound event recognition of domestic robots"],"prefix":"10.1007","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1558-3099","authenticated-orcid":false,"given":"Csaba","family":"Kert\u00e9sz","sequence":"first","affiliation":[]},{"given":"Markku","family":"Turunen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,8,28]]},"reference":[{"key":"258_CR1","doi-asserted-by":"crossref","unstructured":"Andrew G, Gao J (2007) Scalable training of L1-regularized log-linear models. In: Proceedings of the 24th international conference on Machine learning, pp 33\u201340","DOI":"10.1145\/1273496.1273501"},{"key":"258_CR2","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1016\/j.patrec.2015.08.027","volume":"68","author":"J Beltr\u00e1n","year":"2015","unstructured":"Beltr\u00e1n J, Ch\u00e1vez E, Favela J (2015) Scalable identification of mixed environmental sounds, recorded from heterogeneous sources. J Pattern Recognit Lett 68:153\u2013160","journal-title":"J Pattern Recognit Lett"},{"issue":"2","key":"258_CR3","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1007\/s10994-006-9019-7","volume":"65","author":"J Bergstra","year":"2006","unstructured":"Bergstra J, Casagrande N, Erhan D et al (2006) Aggregate features and AdaBoost for music classification. J Mach Learn 65(2):473\u2013484","journal-title":"J Mach Learn"},{"key":"258_CR4","doi-asserted-by":"crossref","unstructured":"Besacier L, Bergamini C, Vaufreydaz D, Castelli E (2001) The effect of speech and audio compression on speech recognition performance. In: Proceedings of the 4th IEEE international symposium on signal processing, pp 301\u2013306","DOI":"10.1109\/MMSP.2001.962750"},{"key":"258_CR5","first-page":"1","volume":"1","author":"M Borsky","year":"2015","unstructured":"Borsky M, Pollak P, Mizera P (2015) Advanced acoustic modelling techniques in MP3 speech recognition. EURASIP J Audio Speech Music Process 1:1\u20137","journal-title":"EURASIP J Audio Speech Music Process"},{"key":"258_CR6","volume-title":"Learning OpenCV","author":"GR Bradski","year":"2008","unstructured":"Bradski GR, Kaehler A (2008) Learning OpenCV, 1st edn. O\u2019Reilly Media, Newton","edition":"1"},{"key":"258_CR7","unstructured":"Bullock J (2007) LibXtract: a lightweight library for audio feature extraction. In: Proceedings of international computer music conference"},{"key":"258_CR8","doi-asserted-by":"crossref","unstructured":"Cakir E, Heittola T, Huttunen H, et al (2016) Polyphonic sound event detection using multi label deep neural networks. In: Proceedings of IEEE international joint conference on neural networks (IJCNN 2016)","DOI":"10.1109\/IJCNN.2015.7280624"},{"key":"258_CR9","unstructured":"Chmulik M, Jarina R (2012) Bio-inspired optimization of acoustic features for generic sound recognition. In: Proceedings of 19th international conference on systems, signals and image processing (IWSSIP), pp 629\u2013632"},{"key":"258_CR10","unstructured":"Choi I, Kwon K, Hyun Bae S, et al (2016) DNN-based sound event detection with exemplar-based approach for noise reduction. In: Proceedings of detection and classification of acoustic scenes and events workshop (DCASE2016)"},{"issue":"6","key":"258_CR11","doi-asserted-by":"publisher","first-page":"1142","DOI":"10.1109\/TASL.2009.2017438","volume":"17","author":"S Chu","year":"2009","unstructured":"Chu S, Narayanan S, Kuo CCJ (2009) Environmental sound recognition with time-frequency audio features. IEEE Trans Audio Speech Lang Process 17(6):1142\u20131158","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"258_CR12","doi-asserted-by":"crossref","unstructured":"Delgado-Contreras JR, Garcia-Vazquez JP, Brena RF (2014) Classification of environmental audio signals using statistical time and frequency features. In: Proceedings of international conference on electronics, communications and computers (CONIELECOMP), pp 212\u2013216","DOI":"10.1109\/CONIELECOMP.2014.6808593"},{"key":"258_CR13","unstructured":"Dennis J (2014) Sound event recognition in unstructured environments using spectrogram image processing. Ph.D. thesis, Nanyang Technological University"},{"key":"258_CR14","doi-asserted-by":"crossref","unstructured":"Foster P, Sigtia S, Krstulovic S, Barkerh J (2015) CHiME-Home: a dataset for sound source recognition in a domestic environment. In: Proceedings of 11th IEEE workshop on applications of signal processing to audio and acoustics (WASPAA)","DOI":"10.1109\/WASPAA.2015.7336899"},{"key":"258_CR15","unstructured":"Goldstein EB (2010) Sensation and perception. Wadsworth, p 490"},{"key":"258_CR16","doi-asserted-by":"crossref","unstructured":"Hertel L, Phan H, Mertins A (2016) Comparing time and frequency domain for audio event recognition using deep learning. In: Proceedings of IEEE international joint conference on neural networks (IJCNN 2016). arXiv:1603.05824","DOI":"10.1109\/IJCNN.2016.7727635"},{"key":"258_CR17","unstructured":"Hsieh C-J, Chang K-W, Lin C-J (2008) A dual coordinate descent method for large-scale linear SVM. In: Proceedings of 25th international conference on machine learning, pp 408\u2013415"},{"key":"258_CR18","unstructured":"Jensen K (1999) Timbre models of musical sounds. Ph.D. dissertation, DIKU report"},{"key":"258_CR19","first-page":"1755","volume":"10","author":"DE King","year":"2009","unstructured":"King DE (2009) Dlib-ml: a machine learning toolkit. J Mach Learn Res 10:1755\u20131758","journal-title":"J Mach Learn Res"},{"key":"258_CR20","doi-asserted-by":"crossref","unstructured":"Maxime J, Alameda-Pineda X, Girin L, Horaud R (2014) Sound representation and classification benchmark for domestic robots. In: Proceedings of IEEE international conference on robotics and automation (ICRA)","DOI":"10.1109\/ICRA.2014.6907786"},{"issue":"3","key":"258_CR21","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1109\/TASLP.2015.2389618","volume":"23","author":"I McLoughlin","year":"2015","unstructured":"McLoughlin I, Zhang H, Xie Z, Song Y, Xiao W (2015) Robust sound event classification using deep neural networks. IEEE\/ACM Trans Audio Speech Lang Process 23(3):540\u2013552","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"258_CR22","unstructured":"Mesaros A, Heittola T, Eronen A, Virtanen T (2010) Acoustic event detection in real life recordings. In: Proceedings of EUSIPCO"},{"key":"258_CR23","unstructured":"Ng PS, Sanches I (2004) The influence of audio compression on speech recognition systems. In: Proceedings of 9th conference on speech and computer"},{"key":"258_CR24","unstructured":"Ness S, Trail S, Driessen P, Schloss A, Tzanetakis G (2011) Music information robotics: coping strategies for musically challenged robots. In: Proceedings of 12th international society for music information retrieval conference (ISMIR), pp 567\u2013572"},{"key":"258_CR25","doi-asserted-by":"crossref","unstructured":"Nouza J, Cerva P, Silovsky J (2013) Adding controlled amount of noise to improve recognition of compressed and spectrally distorted speech. In: Proceedings of IEEE international conference on acoustics, speech and signal processing, pp 8046\u20138050","DOI":"10.1109\/ICASSP.2013.6639232"},{"issue":"1","key":"258_CR26","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/TASLP.2014.2367814","volume":"23","author":"H Phan","year":"2015","unstructured":"Phan H, Maas M, Mazur R, Mertins A (2015) Random regression forests for acoustic event detection and classification. IEEE\/ACM Trans Audio Speech Lang Process 23(1):20\u201331","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"258_CR27","doi-asserted-by":"crossref","unstructured":"Phan H, Hertel L, Maass M, et al (2016) Robust audio event recognition with 1-max pooling convolutional neural networks. In: Proceedings of 17th annual conference of the interenational speech communication association (INTERSPEECH 2016). arXiv:1604.06338","DOI":"10.21437\/Interspeech.2016-123"},{"key":"258_CR28","doi-asserted-by":"crossref","unstructured":"Plinge A, Grzeszick R, Fink G A (2014) A bag-of-features approach to acoustic event detection. In: Proceedings of IEEE international conference on acoustics, speech, and signal processing","DOI":"10.1109\/ICASSP.2014.6854293"},{"key":"258_CR29","unstructured":"Pollak P, Behunek M (2011) Accuracy of MP3 speech recognition under real-word conditions: experimental study. In: Proceedings of IEEE signal processing and multimedia applications (SIGMAP), pp 1\u20136"},{"key":"258_CR30","first-page":"162","volume":"51","author":"HF Pollard","year":"1982","unstructured":"Pollard HF, Jansson EV (1982) A tristimulus method for the specification of musical timbre. J Acust 51:162\u2013171","journal-title":"J Acust"},{"key":"258_CR31","doi-asserted-by":"crossref","unstructured":"Ruiz-Martinez CA, Akhtar MT, Washizawa Y, Escamilla-Hernandez E (2013) On investigating efficient methodology for environmental sound recognition. In: Proceedings of international symposium on intelligent signal processing and communications systems (ISPACS), pp 210\u2013214","DOI":"10.1109\/ISPACS.2013.6704548"},{"issue":"12","key":"258_CR32","doi-asserted-by":"publisher","first-page":"2831","DOI":"10.1109\/TBME.2008.923769","volume":"55","author":"N S\u00e1enz-Lech\u00f3n","year":"2008","unstructured":"S\u00e1enz-Lech\u00f3n N, Osma-Ruiz V, Godino-Llorente JI (2008) Effects of audio compression in automatic detection of voice pathologies. IEEE Trans Biomed Eng 55(12):2831\u20132835","journal-title":"IEEE Trans Biomed Eng"},{"key":"258_CR33","doi-asserted-by":"crossref","unstructured":"Salamon J, Jakoby C, Bello J P (2014) A dataset and taxonomy for urban sound research. In: Proceedings 22nd ACM international conference on multimedia, pp 1041\u20131044","DOI":"10.1145\/2647868.2655045"},{"issue":"1","key":"258_CR34","first-page":"85","volume":"1","author":"M Sebban\u00fc","year":"2000","unstructured":"Sebban\u00fc M, Nock R, Chauchat J, Rakotomalala R (2000) Impact of learning set quality and size on decision tree performances. Int J Comput Syst Signals 1(1):85\u2013105","journal-title":"Int J Comput Syst Signals"},{"issue":"10","key":"258_CR35","doi-asserted-by":"publisher","first-page":"1733","DOI":"10.1109\/TMM.2015.2428998","volume":"17","author":"D Stowell","year":"2015","unstructured":"Stowell D, Stowell D, Benetos E, Lagrange M, Plumbley MD (2015) Detection and classification of acoustic scenes and events. IEEE Trans Multimed 17(10):1733\u20131746","journal-title":"IEEE Trans Multimed"},{"issue":"4","key":"258_CR36","first-page":"631","volume":"8","author":"H Sug","year":"2009","unstructured":"Sug H (2009) An effective sampling method for decision trees considering comprehensibility and accuracy. WSEAS Trans Comput 8(4):631\u2013640","journal-title":"WSEAS Trans Comput"},{"key":"258_CR37","doi-asserted-by":"crossref","unstructured":"Terence NWZ, Dat TH, Dennis J, Siong CE (2013) A robust sound event recognition framework under TV playing conditions. In: Proceedings of signal and information processing association annual summit and conference (APSIPA), pp 1\u20135","DOI":"10.1109\/APSIPA.2013.6694265"},{"key":"258_CR38","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1007\/978-3-319-07064-3_32","volume-title":"Artificial Intelligence: Methods and Applications","author":"Theodoros Theodorou","year":"2014","unstructured":"Theodorou T, Mporas I, Fakotakis N (2014) Audio feature selection for recognition of non-linguistic vocalization sounds. In: Proceedings of Hellenic conference on artificial intelligence, pp 395\u2013405"},{"key":"258_CR39","doi-asserted-by":"crossref","unstructured":"Tsuruoka Y, Tsujii J, Ananiadou S (2009) Stochastic gradient descent training for L1-regularized log-linear models with cumulative penalty. In: Proceedings of ACL-IJCNLP, pp 477\u2013485","DOI":"10.3115\/1687878.1687946"},{"key":"258_CR40","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/978-3-319-04117-9_34","volume-title":"MultiMedia Modeling","author":"Aiko Uemura","year":"2014","unstructured":"Uemura A, Kazumasa I, Katto J (2014) Effects of audio compression on chord recognition. In: Proceedings of international conference on multimedia modeling, pp 345\u2013352"},{"key":"258_CR41","unstructured":"Urbano J, Bogdanov D, Herrera P, G\u00f3mez E, Serra X (2014) What is the effect of audio quality on the robustness of MFCCs and chroma features? In: Proceedings of 15th ISMIR conference, pp 573\u2013578"},{"key":"258_CR42","doi-asserted-by":"crossref","unstructured":"Wang Y, Neves L, Metze F (2016) Audio-based multimedia event detection using deep recurrent neural networks. In: Proceedings of IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 2742\u20132746","DOI":"10.1109\/ICASSP.2016.7472176"},{"key":"258_CR43","doi-asserted-by":"crossref","unstructured":"Yamamoto S, Nakadai K, Nakano M, et al (2006) Real-time robot audition system that recognizes simultaneous speech in the real world. In: Proceedings of international conference on intelligent robots and systems (IROS), pp 5333\u20135338","DOI":"10.1109\/IROS.2006.282037"}],"container-title":["Intelligent Service Robotics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11370-018-0258-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11370-018-0258-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11370-018-0258-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,30]],"date-time":"2022-08-30T20:34:40Z","timestamp":1661891680000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11370-018-0258-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8,28]]},"references-count":43,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2018,10]]}},"alternative-id":["258"],"URL":"https:\/\/doi.org\/10.1007\/s11370-018-0258-9","relation":{},"ISSN":["1861-2776","1861-2784"],"issn-type":[{"value":"1861-2776","type":"print"},{"value":"1861-2784","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,8,28]]},"assertion":[{"value":"2 September 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 August 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}