{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T15:12:59Z","timestamp":1743001979320,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":17,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540342021"},{"type":"electronic","value":"9783540342038"}],"license":[{"start":{"date-parts":[[2006,1,1]],"date-time":"2006-01-01T00:00:00Z","timestamp":1136073600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11754336_8","type":"book-chapter","created":{"date-parts":[[2006,5,2]],"date-time":"2006-05-02T12:25:34Z","timestamp":1146572734000},"page":"78-88","source":"Crossref","is-referenced-by-count":1,"title":["Voice Activity Detection Using Wavelet-Based Multiresolution Spectrum and Support Vector Machines and Audio Mixing Algorithm"],"prefix":"10.1007","author":[{"given":"Wei","family":"Xue","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sidan","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengzhi","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingxian","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"8_CR1","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1109\/89.905996","volume":"9","author":"E. Nemer","year":"2001","unstructured":"Nemer, E., Goubran, R., Mahmoud, S.: Robust voice activity detection using higher-order statistics in the LPC residual domain. IEEE Transactions on Speech and Audio Processing\u00a09, 217\u2013231 (2001)","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Junqua, J.C., Reaves, B., Mak, B.: A study of endpoint detection algorithms in adverse conditions: Incidence on a DTW and HMM recognize. In: Proc. Eurospeech 1991, pp. 371\u20131374 (1991)","DOI":"10.21437\/Eurospeech.1991-313"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Sangwan, A., Chiranth, M.C., Jamadagni, H.S., Sah, R., Prasad, R.V., Gaurav, V.: VAD techniques for real-time speech transmission on the Internet. In: IEEE International Conference on High-Speed Networks and Multimedia Communications, pp. 46\u201350 (2002)","DOI":"10.1109\/HSNMC.2002.1032545"},{"issue":"1","key":"8_CR4","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1109\/TNN.2002.806626","volume":"14","author":"G. Guo","year":"2003","unstructured":"Guo, G., Li, S.Z.: Content-Based Audio Classificationand Retrieval by Support VectorMachines. IEEE Trans. on Neural Networks\u00a014(1), 209\u2013215 (2003)","journal-title":"IEEE Trans. on Neural Networks"},{"key":"8_CR5","unstructured":"Stegmann, J., Schroeder, G.: Robust Voice Activity Detection Based on the Wavelet Transform. In: Proc. IEEE Workshop on Speech Coding, September 7-10, 1997, pp. 99\u2013100 (1997)"},{"issue":"5","key":"8_CR6","doi-asserted-by":"publisher","first-page":"644","DOI":"10.1109\/TSA.2005.851880","volume":"13","author":"C.-C. Lin","year":"2005","unstructured":"Lin, C.-C., Chen, S.-H., Truong, T.K., Chang, Y.: Audio Classification and Categorization Based on Wavelets and Support Vector Machine. IEEE Transactions on Speech and Audio Processing\u00a013(5), 644\u2013651 (2005)","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"8_CR7","unstructured":"ETSI: Draft Recommendation prETS 300 724: GSM Enhanced Full Rate (EFR) speech codec (1996)"},{"key":"8_CR8","unstructured":"ITU-T: Draft Recommendation G.729, Annex B: Voice Activity Detection (1996)"},{"key":"8_CR9","volume-title":"Fundamentals of Speech Recognition","author":"L. Rabiner","year":"1993","unstructured":"Rabiner, L., Juang, B.H.: Fundamentals of Speech Recognition. Prentice-Hall, Englewood Cliffs, NJ (1993)"},{"key":"8_CR10","unstructured":"Agust\u00edn, J.G., Hussein, A.W.: Audio mixing for interactive multimedia communications. In: JCIS 1998, Research Triangle, NC, pp. 217\u2013220 (1998)"},{"key":"8_CR11","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/S0140-3664(01)00333-4","volume":"25","author":"S. Yang","year":"2002","unstructured":"Yang, S., Yu, S., Zhou, J.: Multipoint communications with speech mixing over IP network. Computer communications\u00a025, 46\u201355 (2002)","journal-title":"Computer communications"},{"issue":"1","key":"8_CR12","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/90.222904","volume":"1","author":"R.P. Venkat","year":"1993","unstructured":"Venkat, R.P., Harrick, M.V., Srinivas, R.: Communication architectures and algorithms for media mixing in multimedia conferences. IEEE\/ACM Trans. on Networking\u00a01(1), 20\u201330 (1993)","journal-title":"IEEE\/ACM Trans. on Networking"},{"key":"8_CR13","first-page":"273","volume":"20","author":"C. Cortes","year":"1995","unstructured":"Cortes, C., Vapnik, C.: Support Vector Networks. Machine Learning\u00a020, 273\u2013297 (1995)","journal-title":"Machine Learning"},{"key":"8_CR14","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970104","volume-title":"Ten Lectures on Wavelets","author":"I. Daubechies","year":"1992","unstructured":"Daubechies, I.: Ten Lectures on Wavelets. SIAM, Philadelphia (1992)"},{"key":"8_CR15","volume-title":"Voice and Speech Processing","author":"W. Thomas Parsons","year":"1986","unstructured":"Thomas Parsons, W.: Voice and Speech Processing. McGraw-Hill Book Company, New York (1986)"},{"key":"8_CR16","unstructured":"Platt, J.C.: A Fast Algorithm for Training Support Vector Machines. Microsoft Research Technical Report MSR-TR-98-14 (April 1998)"},{"issue":"6","key":"8_CR17","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1631\/jzus.2005.A0507","volume":"6a","author":"F. Xing","year":"2005","unstructured":"Xing, F., Gu, W.-k.: Research on fast real-time adaptive audio mixing in multimedia conference. Journal of Zhejiang University Science\u00a06a(6), 507\u2013512 (2005)","journal-title":"Journal of Zhejiang University Science"}],"container-title":["Lecture Notes in Computer Science","Computer Vision in Human-Computer Interaction"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11754336_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T19:51:10Z","timestamp":1736365870000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11754336_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540342021","9783540342038"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/11754336_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}