{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T13:57:07Z","timestamp":1760709427423},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2017,10,16]],"date-time":"2017-10-16T00:00:00Z","timestamp":1508112000000},"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":["Int J Speech Technol"],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1007\/s10772-017-9464-7","type":"journal-article","created":{"date-parts":[[2017,10,16]],"date-time":"2017-10-16T10:33:51Z","timestamp":1508150031000},"page":"1023-1036","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Clean speech\/speech with background music classification using HNGD spectrum"],"prefix":"10.1007","volume":"20","author":[{"given":"Banriskhem K.","family":"Khonglah","sequence":"first","affiliation":[]},{"given":"S. R. Mahadeva","family":"Prasanna","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,10,16]]},"reference":[{"key":"9464_CR1","doi-asserted-by":"crossref","unstructured":"Anand\u00a0Joseph, M., Guruprasad, S., & Yegnanarayana, B. (2006). Extracting formants from short segments of speech using group delay functions.","DOI":"10.21437\/Interspeech.2006-327"},{"issue":"6","key":"9464_CR2","doi-asserted-by":"crossref","first-page":"782","DOI":"10.1016\/j.specom.2013.02.007","volume":"55","author":"Y Bayya","year":"2013","unstructured":"Bayya, Y., & Gowda, D. N. (2013). Spectro-temporal analysis of speech signals using zero-time windowing and group delay function. Speech Communication, 55(6), 782\u2013795.","journal-title":"Speech Communication"},{"issue":"1","key":"9464_CR3","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/S0167-6393(01)00062-0","volume":"37","author":"P Beyerlein","year":"2002","unstructured":"Beyerlein, P., Aubert, X., Haeb-Umbach, R., Harris, M., Klakow, D., Wendemuth, A., et al. (2002). Large vocabulary continuous speech recognition of broadcast news-the philips\/rwth approach. Speech Communication, 37(1), 109\u2013131.","journal-title":"Speech Communication"},{"key":"9464_CR4","first-page":"99","volume":"35","author":"A Bhattacharyya","year":"1943","unstructured":"Bhattacharyya, A. (1943). On a measure of divergence between two statistical populations defined by their probability distribution. Bulletin of the Calcutta Mathematical Society, 35, 99\u2013109.","journal-title":"Bulletin of the Calcutta Mathematical Society"},{"issue":"1","key":"9464_CR5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13636-014-0034-5","volume":"2014","author":"D Cast\u00e1n","year":"2014","unstructured":"Cast\u00e1n, D., Ortega, A., Miguel, A., & Lleida, E. (2014). Audio segmentation-by-classification approach based on factor analysis in broadcast news domain. EURASIP Journal on Audio, Speech, and Music Processing, 2014(1), 1\u201313.","journal-title":"EURASIP Journal on Audio, Speech, and Music Processing"},{"key":"9464_CR6","unstructured":"Chang, C.-C., & Lin, C.-J. (2011). LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2, 27:1\u201327:27. http:\/\/www.csie.ntu.edu.tw\/~cjlin\/libsvm ."},{"issue":"2","key":"9464_CR7","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1145\/328236.328148","volume":"43","author":"J Gauvain","year":"2000","unstructured":"Gauvain, J., Lamel, L., & Adda, G. (2000). Transcribing broadcast news for audio and video indexing. Communications of the ACM, 43(2), 64\u201370.","journal-title":"Communications of the ACM"},{"issue":"1","key":"9464_CR8","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/S0167-6393(01)00061-9","volume":"37","author":"J-L Gauvain","year":"2002","unstructured":"Gauvain, J.-L., Lamel, L., & Adda, G. (2002). The limsi broadcast news transcription system. Speech Communication, 37(1), 89\u2013108.","journal-title":"Speech Communication"},{"key":"9464_CR9","unstructured":"Jiang, D.-N., Lu, L., Zhang, H.-J., Tao, J.-H., & Cai, L.-H. (2002). Music type classification by spectral contrast feature. In Proceedings 2002 IEEE international conference on multimedia and expo, 2002 (ICME\u201902) (Vol.\u00a01, pp. 113\u2013116). IEEE."},{"key":"9464_CR10","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1016\/j.dsp.2015.09.005","volume":"48","author":"BK Khonglah","year":"2016","unstructured":"Khonglah, B. K., & Prasanna, S. M. (2016). Speech\/music classification using speech-specific features. Digital Signal Processing, 48, 71\u201383.","journal-title":"Digital Signal Processing"},{"key":"9464_CR11","doi-asserted-by":"crossref","first-page":"1602","DOI":"10.1109\/TASL.2008.2004526","volume":"16","author":"KSR Murthy","year":"2008","unstructured":"Murthy, K. S. R., & Yegnanarayana, B. (2008). Epoch extraction from speech signals. IEEE Transactions on Audio, Speech, and Language Processing, 16, 1602\u20131613.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"1\u20132","key":"9464_CR12","first-page":"213230","volume":"38","author":"L Nguyen","year":"2002","unstructured":"Nguyen, L., Matsoukas, S., Davenport, J., Kubala, F., Schwartz, R., & Makhoul, J. (2002). Progress in transcription of broadcast news using byblos. Speech Communication, 38(1\u20132), 213230.","journal-title":"Speech Communication"},{"key":"9464_CR13","volume-title":"Digital signal processing","author":"A\u00a0V Oppenheim","year":"1975","unstructured":"Oppenheim, A\u00a0. V., & Schafer, R\u00a0. W. (1975). Digital signal processing. New Delhi: Prentice-Hall."},{"key":"9464_CR14","doi-asserted-by":"crossref","unstructured":"Prasad, R., & Yegnanarayana, B. (2013). Acoustic segmentation of speech using zero time liftering (ztl) (pp. 2292\u20132296).","DOI":"10.21437\/Interspeech.2013-537"},{"issue":"1","key":"9464_CR15","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1016\/S0167-6393(00)00020-0","volume":"32","author":"S Renals","year":"2000","unstructured":"Renals, S., Abberley, D., Kirby, D., & Robinson, T. (2000). Indexing and retrieval of broadcast news. Speech Communication, 32(1), 5\u201320.","journal-title":"Speech Communication"},{"key":"9464_CR16","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1016\/j.specom.2017.06.003","volume":"92","author":"BD Sarma","year":"2017","unstructured":"Sarma, B.\u00a0D., Prasanna, S.\u00a0M., & Sarmah, P. (2017). Consonant-vowel unit recognition using dominant aperiodic and transition region detection. Speech Communication, 92, 77\u201389.","journal-title":"Speech Communication"},{"key":"9464_CR17","doi-asserted-by":"crossref","first-page":"1331","DOI":"10.1109\/ICASSP.1997.596192","volume":"2","author":"E Scheirer","year":"1997","unstructured":"Scheirer, E., & Slaney, M. (1997). Construction and evaluation of a robust multifeature speech\/music discriminator. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing., 2, 1331\u20131334.","journal-title":"Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing."},{"key":"9464_CR18","doi-asserted-by":"crossref","unstructured":"Sell, G., & Clark, P. (2014). Music tonality features for speech\/music discrimination. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 2489\u20132493). IEEE.","DOI":"10.1109\/ICASSP.2014.6854048"},{"key":"9464_CR19","unstructured":"Siegler, M.\u00a0A., Jain, U., Raj, B., & Stern, R.\u00a0M. (1997). Automatic segmentation, classification and clustering of broadcast news audio. In Proceedings of DARPA Speech Recognition Workshop (pp. 97\u201399)."},{"issue":"9","key":"9464_CR20","doi-asserted-by":"crossref","first-page":"2613","DOI":"10.1109\/TASL.2012.2207114","volume":"20","author":"KS Srinivas","year":"2012","unstructured":"Srinivas, K. S., & Prahallad, K. (2012). An fir implementation of zero frequency filtering of speech signals. IEEE Transactions on Audio, Speech, and Language Processing, 20(9), 2613\u20132617.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9464_CR21","doi-asserted-by":"crossref","unstructured":"Tzanetakis, G., & Cook, P. (2000). Sound analysis using mpeg compressed audio. In Proceedings IEEE international conference on acoustics, speech, and signal processing, 2000 (ICASSP\u201900) (Vol.\u00a02, pp. II761\u2013II764).","DOI":"10.1109\/ICASSP.2000.859071"},{"key":"9464_CR22","doi-asserted-by":"crossref","unstructured":"Vavrek, J., Voz\u00e1rikov\u00e1, E., Pleva, M., & Juh\u00e1r, J. (2012). Broadcast news audio classification using svm binary trees. In 2012 35th international conference on telecommunications and signal processing (TSP) (pp. 469\u2013473). IEEE","DOI":"10.1109\/TSP.2012.6256338"},{"key":"9464_CR23","first-page":"33","volume":"1","author":"S Wegmann","year":"1999","unstructured":"Wegmann, S., Zhan, P., & Gillick, L. (1999). Progress in broadcast news transcription at dragon systems. IEEE International Conference on Acoustics, Speech, and Signal Processing, 1, 33\u201336.","journal-title":"IEEE International Conference on Acoustics, Speech, and Signal Processing."},{"issue":"1\u20132","key":"9464_CR24","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/S0167-6393(01)00059-0","volume":"37","author":"P Woodland","year":"2002","unstructured":"Woodland, P. (2002). The development of the htk broadcast news transcription system: An overview. Speech Communication, 37(1\u20132), 47\u201367.","journal-title":"Speech Communication"},{"issue":"5","key":"9464_CR25","doi-asserted-by":"crossref","first-page":"1638","DOI":"10.1121\/1.381864","volume":"63","author":"B Yegnanarayana","year":"1978","unstructured":"Yegnanarayana, B. (1978). Formant extraction from linear-prediction phase spectra. The Journal of the Acoustical Society of America, 63(5), 1638\u20131640.","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"9","key":"9464_CR26","doi-asserted-by":"crossref","first-page":"2281","DOI":"10.1109\/78.157227","volume":"40","author":"B Yegnanarayana","year":"1992","unstructured":"Yegnanarayana, B., & Murthy, H. A. (1992). Significance of group delay functions in spectrum estimation. IEEE Transactions on Signal Processing, 40(9), 2281\u20132289.","journal-title":"IEEE Transactions on Signal Processing"},{"issue":"4","key":"9464_CR27","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1109\/89.917689","volume":"9","author":"T Zhang","year":"2001","unstructured":"Zhang, T., & Kuo, C. J. (2001). Audio content analysis for online audiovisual data segmentation and classification. IEEE Transactions on Speech and Audio Processing, 9(4), 441\u2013457.","journal-title":"IEEE Transactions on Speech and Audio Processing"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-017-9464-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-017-9464-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-017-9464-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,27]],"date-time":"2023-08-27T05:48:33Z","timestamp":1693115313000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-017-9464-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10,16]]},"references-count":27,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2017,12]]}},"alternative-id":["9464"],"URL":"https:\/\/doi.org\/10.1007\/s10772-017-9464-7","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,10,16]]}}}