{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:51:52Z","timestamp":1740099112003,"version":"3.37.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319937632"},{"type":"electronic","value":"9783319937649"}],"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\/978-3-319-93764-9_32","type":"book-chapter","created":{"date-parts":[[2018,6,5]],"date-time":"2018-06-05T03:09:12Z","timestamp":1528168152000},"page":"340-350","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Multi-Resolution Fully Convolutional Neural Networks for Monaural Audio Source Separation"],"prefix":"10.1007","author":[{"given":"Emad M.","family":"Grais","sequence":"first","affiliation":[]},{"given":"Hagen","family":"Wierstorf","sequence":"additional","affiliation":[]},{"given":"Dominic","family":"Ward","sequence":"additional","affiliation":[]},{"given":"Mark D.","family":"Plumbley","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,6,6]]},"reference":[{"key":"32_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-32845-9","volume-title":"Signal Processing Methods for Music Transcription","author":"A Klapuri","year":"2007","unstructured":"Klapuri, A., Davy, M.: Signal Processing Methods for Music Transcription. Springer, Boston (2007). https:\/\/doi.org\/10.1007\/0-387-32845-9"},{"key":"32_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1007\/978-3-319-53547-0_25","volume-title":"Latent Variable Analysis and Signal Separation","author":"P Chandna","year":"2017","unstructured":"Chandna, P., Miron, M., Janer, J., G\u00f3mez, E.: Monoaural audio source separation using deep convolutional neural networks. In: Tichavsk\u00fd, P., Babaie-Zadeh, M., Michel, O.J.J., Thirion-Moreau, N. (eds.) LVA\/ICA 2017. LNCS, vol. 10169, pp. 258\u2013266. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-53547-0_25"},{"key":"32_CR3","unstructured":"Chollet, F.: Keras (2015). https:\/\/github.com\/fchollet\/keras"},{"key":"32_CR4","unstructured":"Dumoulin, V., Visin, F.: A guide to convolution arithmetic for deep learning. arXiv:1603.07285 (2016)"},{"key":"32_CR5","first-page":"1","volume":"26","author":"M Espi","year":"2015","unstructured":"Espi, M., Fujimoto, M., Kinoshita, K., Nakatani, T.: Exploiting spectro-temporal locality in deep learning based acoustic event detection. EURASIP J. Audio Speech Music Process. 26, 1\u201312 (2015)","journal-title":"EURASIP J. Audio Speech Music Process."},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Grais, E.M., Plumbley, M.D.: Single channel audio source separation using convolutional denoising autoencoders. In: Proceedings of GlobalSIP (2017)","DOI":"10.1109\/GlobalSIP.2017.8309164"},{"key":"32_CR7","doi-asserted-by":"crossref","unstructured":"Grais, E.M., Roma, G., Simpson, A.J.R., Plumbley, M.D.: Combining mask estimates for single channel audio source separation using deep neural networks. In: Proceedings of InterSpeech (2016)","DOI":"10.21437\/Interspeech.2016-216"},{"key":"32_CR8","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316672","volume-title":"Multiple Comparison Procedures","author":"Y Hochberg","year":"1987","unstructured":"Hochberg, Y., Tamhane, A.C.: Multiple Comparison Procedures. Wiley, New York (1987). https:\/\/doi.org\/10.1002\/9780470316672"},{"key":"32_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1007\/978-3-319-47157-0_20","volume-title":"Machine Learning in Medical Imaging","author":"J Kawahara","year":"2016","unstructured":"Kawahara, J., Hamarneh, G.: Multi-resolution-Tract CNN with hybrid pretrained and skin-lesion trained layers. In: Wang, L., Adeli, E., Wang, Q., Shi, Y., Suk, H.-I. (eds.) MLMI 2016. LNCS, vol. 10019, pp. 164\u2013171. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-47157-0_20"},{"key":"32_CR10","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. In: Proc. arXiv:1412.6980 and presented at ICLR (2015)"},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"Lim, W., Lee, T.: Harmonic and percussive source separation using a convolutional auto encoder. In: Proceedings of EUSIPCO (2017)","DOI":"10.23919\/EUSIPCO.2017.8081520"},{"key":"32_CR12","unstructured":"Miron, M., Janer, J., Gomez, E.: Monaural score-informed source separation for classical music using convolutional neural networks. In: Proceedings of ISMIR (2017)"},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"Naderi, N., Nasersharif, B.: Multiresolution convolutional neural network for robust speech recognition. In: Proceedings of ICEE (2017)","DOI":"10.1109\/IranianCEE.2017.7985272"},{"key":"32_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/978-3-319-22482-4_45","volume-title":"Latent Variable Analysis and Signal Separation","author":"N Ono","year":"2015","unstructured":"Ono, N., Rafii, Z., Kitamura, D., Ito, N., Liutkus, A.: The 2015 signal separation evaluation campaign. In: Vincent, E., Yeredor, A., Koldovsk\u00fd, Z., Tichavsk\u00fd, P. (eds.) LVA\/ICA 2015. LNCS, vol. 9237, pp. 387\u2013395. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-22482-4_45"},{"key":"32_CR15","doi-asserted-by":"crossref","unstructured":"Park, S.R., Lee, J.W.: A fully convolutional neural network for speech enhancement. In: Proceedings of Interspeech (2017)","DOI":"10.21437\/Interspeech.2017-1465"},{"key":"32_CR16","unstructured":"Simpson, A.J.: Time-frequency trade-offs for audio source separation with binary masks. arXiv:1504.07372 (2015)"},{"key":"32_CR17","unstructured":"Tang, Y., Mohamed, A.: Multi resolution deep belief networks. In: Proceedings of AISTATS (2012)"},{"key":"32_CR18","doi-asserted-by":"crossref","unstructured":"Venkataramani, S., Smaragdis, P.: End-to-end source separation with adaptive front-ends. In: Proceedings of WASPAA (2017)","DOI":"10.1109\/ACSSC.2018.8645535"},{"issue":"4","key":"32_CR19","doi-asserted-by":"publisher","first-page":"1462","DOI":"10.1109\/TSA.2005.858005","volume":"14","author":"E Vincent","year":"2006","unstructured":"Vincent, E., Gribonval, R., Fevotte, C.: Performance measurement in blind audio source separation. IEEE Trans. Audio Speech Lang. Process. 14(4), 1462\u20131469 (2006)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"32_CR20","doi-asserted-by":"publisher","first-page":"1066","DOI":"10.1109\/TASL.2006.885253","volume":"15","author":"T Virtanen","year":"2007","unstructured":"Virtanen, T.: Monaural sound source separation by non-negative matrix factorization with temporal continuity and sparseness criteria. IEEE Trans. Audio Speech Lang. Process. 15, 1066\u20131074 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"32_CR21","unstructured":"Wenjie, L., Yujia, L., Raquel, U., Richard, Z.: Understanding the effective receptive field in deep convolutional neural networks. In: Proceedings of NIPS, pp. 4898\u20134906 (2016)"},{"issue":"6","key":"32_CR22","doi-asserted-by":"publisher","first-page":"80","DOI":"10.2307\/3001968","volume":"1","author":"F Wilcoxon","year":"1945","unstructured":"Wilcoxon, F.: Individual comparisons by ranking methods. Biometrics Bullet. 1(6), 80\u201383 (1945)","journal-title":"Biometrics Bullet."},{"key":"32_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"564","DOI":"10.1007\/978-3-319-46675-0_62","volume-title":"Neural Information Processing","author":"W Xue","year":"2016","unstructured":"Xue, W., Zhao, H., Zhang, L.: Encoding multi-resolution two-stream CNNs for action recognition. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds.) ICONIP 2016. LNCS, vol. 9949, pp. 564\u2013571. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46675-0_62"},{"key":"32_CR24","doi-asserted-by":"crossref","unstructured":"Zhao, M., Wang, D., Zhang, Z., Zhang, X.: Music removal by convolutional denoising autoencoder in speech recognition. In: Proceedings of APSIPA (2016)","DOI":"10.1109\/APSIPA.2015.7415289"}],"container-title":["Lecture Notes in Computer Science","Latent Variable Analysis and Signal Separation"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-93764-9_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,18]],"date-time":"2019-10-18T22:34:31Z","timestamp":1571438071000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-93764-9_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319937632","9783319937649"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-93764-9_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}