{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T04:10:18Z","timestamp":1748059818306,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030199081"},{"type":"electronic","value":"9783030199098"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-19909-8_16","type":"book-chapter","created":{"date-parts":[[2019,5,15]],"date-time":"2019-05-15T00:24:22Z","timestamp":1557879862000},"page":"184-195","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Recognition of Urban Sound Events Using Deep Context-Aware Feature Extractors and Handcrafted Features"],"prefix":"10.1007","author":[{"given":"Theodore","family":"Giannakopoulos","sequence":"first","affiliation":[]},{"given":"Evaggelos","family":"Spyrou","sequence":"additional","affiliation":[]},{"given":"Stavros J.","family":"Perantonis","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,5,15]]},"reference":[{"key":"16_CR1","unstructured":"Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016)"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Choi, K., Fazekas, G., Sandler, M.: Explaining deep convolutional neural networks on music classification. arXiv preprint arXiv:1607.02444 (2016)","DOI":"10.1109\/ICASSP.2017.7952585"},{"issue":"1","key":"16_CR3","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","volume":"20","author":"GE Dahl","year":"2012","unstructured":"Dahl, G.E., Yu, D., Deng, L., Acero, A.: Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Trans. Audio Speech Lang. Process. 20(1), 30\u201342 (2012)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"12","key":"16_CR4","doi-asserted-by":"publisher","first-page":"e0144610","DOI":"10.1371\/journal.pone.0144610","volume":"10","author":"T Giannakopoulos","year":"2015","unstructured":"Giannakopoulos, T.: pyaudioanalysis: an open-source python library for audio signal analysis. PloS One 10(12), e0144610 (2015)","journal-title":"PloS One"},{"key":"16_CR5","volume-title":"Introduction to Audio Analysis: A MATLAB\u00ae Approach","author":"T Giannakopoulos","year":"2014","unstructured":"Giannakopoulos, T., Pikrakis, A.: Introduction to Audio Analysis: A MATLAB\u00ae Approach. Academic Press, Cambridge (2014)"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Giannakopoulos, T., Siantikos, G., Perantonis, S., Votsi, N.E., Pantis, J.: Automatic soundscape quality estimation using audio analysis. In: Proceedings of the 8th ACM International Conference on PErvasive Technologies Related to Assistive Environments, p. 19. ACM (2015)","DOI":"10.1145\/2769493.2769501"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Grill, T., Schluter, J.: Music boundary detection using neural networks on spectrograms and self-similarity lag matrices. In: 2015 23rd European Signal Processing Conference (EUSIPCO), pp. 1296\u20131300. IEEE (2015)","DOI":"10.1109\/EUSIPCO.2015.7362593"},{"issue":"6","key":"16_CR8","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., et al.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process. Mag. 29(6), 82\u201397 (2012)","journal-title":"IEEE Signal Process. Mag."},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Huang, Z., Dong, M., Mao, Q., Zhan, Y.: Speech emotion recognition using CNN. In: Proceedings of the 22nd ACM International Conference on Multimedia, pp. 801\u2013804. ACM (2014)","DOI":"10.1145\/2647868.2654984"},{"key":"16_CR10","unstructured":"Huzaifah, M.: Comparison of time-frequency representations for environmental sound classification using convolutional neural networks. arXiv preprint arXiv:1706.07156 (2017)"},{"key":"16_CR11","volume-title":"MPEG-7 Audio and Beyond: Audio Content Indexing and Retrieval","author":"K Hyoung-Gook","year":"2005","unstructured":"Hyoung-Gook, K., Nicolas, M., Sikora, T.: MPEG-7 Audio and Beyond: Audio Content Indexing and Retrieval. Wiley, Hoboken (2005)"},{"key":"16_CR12","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.ins.2013.04.014","volume":"243","author":"P Khunarsal","year":"2013","unstructured":"Khunarsal, P., Lursinsap, C., Raicharoen, T.: Very short time environmental sound classification based on spectrogram pattern matching. Inf. Sci. 243, 57\u201374 (2013)","journal-title":"Inf. Sci."},{"key":"16_CR13","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"issue":"2","key":"16_CR14","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1023\/A:1022859003006","volume":"51","author":"LI Kuncheva","year":"2003","unstructured":"Kuncheva, L.I., Whitaker, C.J.: Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy. Mach. Learn. 51(2), 181\u2013207 (2003)","journal-title":"Mach. Learn."},{"key":"16_CR15","unstructured":"Lee, H., Pham, P., Largman, Y., Ng, A.Y.: Unsupervised feature learning for audio classification using convolutional deep belief networks. In: Advances in Neural Information Processing Systems, pp. 1096\u20131104 (2009)"},{"key":"16_CR16","unstructured":"Mesaros, A., et al.: DCASE 2017 challenge setup: tasks, datasets and baseline system. In: DCASE 2017-Workshop on Detection and Classification of Acoustic Scenes and Events (2017)"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Mesaros, A., Heittola, T., Virtanen, T.: TUT database for acoustic scene classification and sound event detection. In: 2016 24th European Signal Processing Conference (EUSIPCO), pp. 1128\u20131132. IEEE (2016)","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Piczak, K.J.: Environmental sound classification with convolutional neural networks. In: 2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP), pp. 1\u20136. IEEE (2015)","DOI":"10.1109\/MLSP.2015.7324337"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Piczak, K.J.: ESC: dataset for environmental sound classification. In: Proceedings of the 23rd ACM International Conference on Multimedia, pp. 1015\u20131018. ACM (2015)","DOI":"10.1145\/2733373.2806390"},{"issue":"3","key":"16_CR20","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1109\/LSP.2017.2657381","volume":"24","author":"J Salamon","year":"2017","unstructured":"Salamon, J., Bello, J.P.: Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal Process. Lett. 24(3), 279\u2013283 (2017)","journal-title":"IEEE Signal Process. Lett."},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Salamon, J., Jacoby, C., Bello, J.P.: A dataset and taxonomy for urban sound research. In: Proceedings of the 22nd ACM international conference on Multimedia, pp. 1041\u20131044. ACM (2014)","DOI":"10.1145\/2647868.2655045"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Scardapane, S., Comminiello, D., Scarpiniti, M., Uncini, A.: Music classification using extreme learning machines. In: 2013 8th International Symposium on Image and Signal Processing and Analysis (ISPA), pp. 377\u2013381. IEEE (2013)","DOI":"10.1109\/ISPA.2013.6703770"},{"key":"16_CR23","unstructured":"Schl\u00fcter, J., B\u00f6ck, S.: CNN-based audio onset detection mirex submission"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Schl\u00fcter, J., B\u00f6ck, S.: Musical onset detection with convolutional neural networks. In: 6th International Workshop on Machine Learning and Music (MML), Prague, Czech Republic (2013)","DOI":"10.1109\/ICASSP.2014.6854953"},{"key":"16_CR25","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","volume":"61","author":"J Schmidhuber","year":"2015","unstructured":"Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85\u2013117 (2015)","journal-title":"Neural Netw."},{"issue":"1","key":"16_CR26","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"16_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1007\/978-3-319-49409-8_27","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"A Subramaniam","year":"2016","unstructured":"Subramaniam, A., Patel, V., Mishra, A., Balasubramanian, P., Mittal, A.: Bi-modal first impressions recognition using temporally ordered deep audio and stochastic visual features. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 337\u2013348. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-49409-8_27"},{"key":"16_CR28","volume-title":"Pattern Recognition","author":"S Theodoridis","year":"2008","unstructured":"Theodoridis, S., Koutroumbas, K.: Pattern Recognition, 4th edn. Academic Press, Cambridge (2008)","edition":"4"},{"issue":"7\/8","key":"16_CR29","doi-asserted-by":"publisher","first-page":"484","DOI":"10.17743\/jaes.2016.0021","volume":"64","author":"M Thorogood","year":"2016","unstructured":"Thorogood, M., Fan, J., Pasquier, P.: Soundscape audio signal classification and segmentation using listeners perception of background and foreground sound. J. Audio Eng. Soc. 64(7\/8), 484\u2013492 (2016)","journal-title":"J. Audio Eng. Soc."},{"key":"16_CR30","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1016\/j.apacoust.2016.08.002","volume":"117","author":"J Ye","year":"2017","unstructured":"Ye, J., Kobayashi, T., Murakawa, M.: Urban sound event classification based on local and global features aggregation. App. Acoust. 117, 246\u2013256 (2017)","journal-title":"App. Acoust."},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, C., Evangelopoulos, G., Voinea, S., Rosasco, L., Poggio, T.: A deep representation for invariance and music classification. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6984\u20136988. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6854954"}],"container-title":["IFIP Advances in Information and Communication Technology","Artificial Intelligence Applications and Innovations"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-19909-8_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T13:41:08Z","timestamp":1684158068000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-19909-8_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030199081","9783030199098"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-19909-8_16","relation":{},"ISSN":["1868-4238","1868-422X"],"issn-type":[{"type":"print","value":"1868-4238"},{"type":"electronic","value":"1868-422X"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"15 May 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Artificial Intelligence Applications and Innovations","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hersonissos","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 May 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 May 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aiai2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.aiai2019.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"101","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"49","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"6","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"49% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}