{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T11:14:58Z","timestamp":1782386098313,"version":"3.54.5"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030007638","type":"print"},{"value":"9783030007645","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-00764-5_2","type":"book-chapter","created":{"date-parts":[[2018,9,17]],"date-time":"2018-09-17T16:21:31Z","timestamp":1537201291000},"page":"14-23","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":57,"title":["Mixup-Based Acoustic Scene Classification Using Multi-channel Convolutional Neural Network"],"prefix":"10.1007","author":[{"given":"Kele","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dawei","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haibo","family":"Mi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boqing","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dezhi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lilun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hengxing","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuwen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,9,18]]},"reference":[{"issue":"3","key":"2_CR1","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1145\/355324.355327","volume":"7","author":"N Sawhney","year":"2000","unstructured":"Sawhney, N., Schmandt, C.: Nomadic radio: speech and audio interaction for contextual messaging in nomadic environments. ACM Trans. Comput. Interact. 7(3), 353\u2013383 (2000)","journal-title":"ACM Trans. Comput. Interact."},{"issue":"10","key":"2_CR2","doi-asserted-by":"publisher","first-page":"1733","DOI":"10.1109\/TMM.2015.2428998","volume":"17","author":"D Stowell","year":"2015","unstructured":"Stowell, D., Giannoulis, D., Benetos, E., Lagrange, M., Plumbley, M.D.: Detection and classification of acoustic scenes and events. IEEE Trans. Multimed. 17(10), 1733\u20131746 (2015)","journal-title":"IEEE Trans. Multimed."},{"key":"2_CR3","unstructured":"Marchi, E., Tonelli, D., Xu, X., Ringeval, F., Deng, J., Squartini, S.: The up system for the 2016 DCASE challenge using deep recurrent neural network and multiscale kernel subspace learning. In: IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE) (2016)"},{"key":"2_CR4","unstructured":"Adavanne, S.: Sound event detection in multichannel audio using spatial and harmonic features. In: IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE) (2016)"},{"key":"2_CR5","unstructured":"Elizalde, B., Lei, H., Friedland, G., Peters, N.: An i-vector based approach for audio scene detection. In: IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE) (2013)"},{"key":"2_CR6","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: Beyond Empirical Risk Minimization. In: International Conference on Learning Representations (2018)"},{"key":"2_CR7","unstructured":"Mesaros, A., et al.: DCASE 2017 challenge setup: tasks, datasets and baseline system. In: IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE) (2017)"},{"issue":"6","key":"2_CR8","doi-asserted-by":"publisher","first-page":"162","DOI":"10.3390\/app6060162","volume":"6","author":"A Mesaros","year":"2016","unstructured":"Mesaros, A., Heittola, T., Virtanen, T.: Metrics for Polyphonic sound event detection. Appl. Sci. 6(6), 162 (2016)","journal-title":"Appl. Sci."},{"issue":"1","key":"2_CR9","first-page":"142","volume":"23","author":"A Rakotomamonjy","year":"2015","unstructured":"Rakotomamonjy, A., Gasso, G.: Histogram of gradients of time-frequency representations for audio scene classification. IEEE\/ACM Trans. Audio Speech Lang. Process. (TASLP) 23(1), 142\u2013153 (2015)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process. (TASLP)"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Salamon, J., Bello, J.P.: Unsupervised feature learning for urban sound classification. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 171\u2013175 (2015)","DOI":"10.1109\/ICASSP.2015.7177954"},{"key":"2_CR11","unstructured":"Eghbal-Zadeh, H.: CP-JKU submissions for DCASE-2016: a hybrid approach using binaural i-vectors and deep convolutional neural networks. In: IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE) (2016)"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Bisot, V., Serizel, R., Essid, S., Richard, G.: Supervised nonnegative matrix factorization for acoustic scene classification. In: IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE) (2016)","DOI":"10.1109\/TASLP.2017.2690570"},{"key":"2_CR13","unstructured":"Schr\u00f6der, J., Anem\u00fcller, J., Goetze, S.: Performance comparison of GMM, HMM and DNN based approaches for acoustic event detection within task 3 of the DCASE 2016 challenge. In: IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE) (2016)"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Phan, H., Hertel, L., Maass, M., Koch, P., Mertins, A.: Label tree embeddings for acoustic scene classification. In: IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE) (2016)","DOI":"10.1145\/2964284.2967268"},{"key":"2_CR15","unstructured":"Han, Y., Lee, K.: Acoustic scene classification using convolutional neural network and multiple-width frequency-delta data augmentation. In: IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE) (2016)"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Xu, Y., Kong, Q., Huang, Q., Wang, W., Plumbley, M.D.: Convolutional gated recurrent neural network incorporating spatial features for audio tagging. arXiv:1702.07787 (2017)","DOI":"10.1109\/IJCNN.2017.7966291"},{"key":"2_CR17","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1\u20139 (2012)"},{"key":"2_CR18","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. IEEE Signal Process. Mag. 29, 82\u201397 (2012)","journal-title":"IEEE Signal Process. Mag."},{"key":"2_CR19","unstructured":"Hertel, L., Phan, H., Mertins, A.: Classifying variable-length audio files with all-convolutional networks and masked global pooling. arXiv:1607.02857 (2016)"},{"issue":"10","key":"2_CR20","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(10), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"2_CR21","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.195"},{"issue":"1","key":"2_CR23","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., 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":"2_CR24","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning (2015)"},{"key":"2_CR25","unstructured":"Mun, S., Park, S., Han D.K., Ko, H.: Generative adversarial network based acoustic scene training set augmentation and selection using SVM hyper-plane. In: IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE) (2017)"}],"container-title":["Lecture Notes in Computer Science","Advances in Multimedia Information Processing \u2013 PCM 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-00764-5_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T12:05:51Z","timestamp":1710331551000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-00764-5_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030007638","9783030007645"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-00764-5_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"18 September 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PCM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim Conference on Multimedia","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hefei","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pcm2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/pcm2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}