{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,29]],"date-time":"2025-06-29T20:40:06Z","timestamp":1751229606577,"version":"3.41.0"},"publisher-location":"Cham","reference-count":13,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319736020"},{"type":"electronic","value":"9783319736037"}],"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\/978-3-319-73603-7_7","type":"book-chapter","created":{"date-parts":[[2018,1,12]],"date-time":"2018-01-12T09:13:02Z","timestamp":1515748382000},"page":"81-92","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["An RNN-Based Speech-Music Discrimination Used for Hybrid Audio Coder"],"prefix":"10.1007","author":[{"given":"Wanzhao","family":"Yang","sequence":"first","affiliation":[]},{"given":"Weiping","family":"Tu","sequence":"additional","affiliation":[]},{"given":"Jiaxi","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Xiong","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yuhong","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Yucheng","family":"Song","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,1,13]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Wang, J., Wu, Q., Deng, H.: Real-time speech\/music classification with a hierarchical oblique decision tree. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 2033\u20132036 (2008)","DOI":"10.1109\/ICASSP.2008.4518039"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Fuchs, G.: A robust speech\/music discriminator for switched audio coding. In: 23rd European Signal Processing Conference, pp. 569\u2013573 (2015)","DOI":"10.1109\/EUSIPCO.2015.7362447"},{"issue":"6","key":"7_CR3","doi-asserted-by":"crossref","first-page":"1830","DOI":"10.1093\/ietisy\/e91-d.6.1830","volume":"91","author":"J Kim","year":"2008","unstructured":"Kim, J., Kim, N.: Improved frame mode selection for AMR-WB+ based on decision tree. IEICE Trans. Inf. Syst. 91(6), 1830\u20131833 (2008)","journal-title":"IEICE Trans. Inf. Syst."},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Wang, M., Lee, M.: A neural network based coding mode selection scheme of hybrid audio coder. In: IEEE International Conference on Wireless Communications, Networking and Information Security, pp. 107\u2013110 (2010)","DOI":"10.1109\/WCINS.2010.5541899"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Khan, M., Al-Khatib, W., Moinuddin, M.: Automatic classification of speech and music using neural networks. In: ACM International Workshop on Multimedia databases, pp. 94\u201399 (2004)","DOI":"10.1145\/1032604.1032620"},{"key":"7_CR6","unstructured":"Pikrakis, A., Theodoridis, S.: Speech-music discrimination: a deep learning perspective. In: 22nd European Signal Processing Conference, pp. 616\u2013620 (2014)"},{"key":"7_CR7","unstructured":"3GPP TR 26.936: 3rd Generation Partnership Project; Technical Specification Group Services and System Aspects; Performance Characterization of Audio Codecs (Release 14) (2017)"},{"issue":"1","key":"7_CR8","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A.: 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":"7_CR9","unstructured":"ETSI TS 126 290: Digital cellular telecommunications system (Phase 2+); Universal Mobile Telecommunications System (UMTS); Audio codec processing functions; Extended Adaptive Multi-Rate - Wideband (AMR-WB+) codec; Transcoding functions (Release 6) (2005)"},{"key":"7_CR10","unstructured":"ISO\/IEC 23003-3, Information Technology \u2013 MPEG Audio Technologies \u2013 Part 3: Unified Speech and Audio Coding, ed. 1, International Organization for Standardization (2011)"},{"key":"7_CR11","unstructured":"GPP TS 26.441: 3rd Generation Partnership Project; Technical Specification Group Services and System Aspects; Codec for Enhanced Voice Services (EVS); General Overview (Release 14) (2017)"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Lee, S., Kim, J., Lee, I.: Speech\/audio signal classification using spectral flux pattern recogniton. In: IEEE Workshop on Signal Processing Systems, pp. 232\u2013236 (2012)","DOI":"10.1109\/SiPS.2012.36"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Khonglah, B., Sharma, R., Mahadeva, S.: Speech vs music discrimination using empirical mode decomposition. In: National Conference on Communications, pp. 1\u20136 (2015)","DOI":"10.1109\/NCC.2015.7084865"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-73603-7_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,29]],"date-time":"2025-06-29T20:24:15Z","timestamp":1751228655000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-73603-7_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319736020","9783319736037"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-73603-7_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}