{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T06:17:23Z","timestamp":1725862643124},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319439570"},{"type":"electronic","value":"9783319439587"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-43958-7_79","type":"book-chapter","created":{"date-parts":[[2016,8,12]],"date-time":"2016-08-12T02:11:41Z","timestamp":1470967901000},"page":"651-658","source":"Crossref","is-referenced-by-count":3,"title":["Speech Recognition Combining MFCCs and Image Features"],"prefix":"10.1007","author":[{"given":"Stamatis","family":"Karlos","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikos","family":"Fazakis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katerina","family":"Karanikola","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sotiris","family":"Kotsiantis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyriakos","family":"Sgarbas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,8,13]]},"reference":[{"key":"79_CR1","doi-asserted-by":"crossref","unstructured":"Yu, G.: Audio Classification From Time-Frequency Texture, Massachusetts Institute of Technology. Ecole Polytechnique, Palaiseau Cedex, NSL, Time, pp. 1677\u20131680 (2009)","DOI":"10.1109\/ICASSP.2009.4959924"},{"key":"79_CR2","doi-asserted-by":"crossref","unstructured":"Muroi, T., Takashima, R., Takiguchi, T., Ariki, Y.: Gradient-based acoustic features for speech recognition. In: International Symposium on Intelligent Signal Processing Communication Systems 2009, ISPACS 2009, pp. 445\u2013448 (2009)","DOI":"10.1109\/ISPACS.2009.5383805"},{"key":"79_CR3","series-title":"Lecture Notes in Electrical Engineering","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1007\/978-3-642-12990-2_38","volume-title":"Advances in Neural Network Research and Applications","author":"P Khunarsa","year":"2010","unstructured":"Khunarsa, P., Lursinsap, C., Raicharoen, T.: Impulsive environment sound detection by neural classification of spectrogram and mel-frequency coefficient images. In: Zeng, Z., Wang, J. (eds.) Advances in Neural Network Research and Applications. LNEE, vol. 67, pp. 337\u2013346. Springer, Heidelberg (2010)"},{"issue":"4","key":"79_CR4","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"SB Davis","year":"1980","unstructured":"Davis, S.B., Mermelstein, P.: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. Trans. Acoust. Speech Signal Process. 28(4), 357\u2013366 (1980)","journal-title":"Trans. Acoust. Speech Signal Process."},{"key":"79_CR5","doi-asserted-by":"crossref","unstructured":"Huang, J., Kumar, S.R., Mitra, M., Zhu, W.-J., Zabih, R.: Image indexing using color correlograms. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 762\u2013768 (1997)","DOI":"10.1109\/CVPR.1997.609412"},{"key":"79_CR6","doi-asserted-by":"crossref","unstructured":"Lux, M., Chatzichristofis, S.A.: Lire: lucene image retrieval. In: Proceedings of the 16th ACM International Conference on Multimedia - MM 2008, p. 1085 (2008)","DOI":"10.1145\/1459359.1459577"},{"key":"79_CR7","doi-asserted-by":"crossref","unstructured":"Lux, M.: Content based image retrieval with LIRe. In: Proceedings of the 19th ACM International Conference on Multimedia, pp. 735\u2013738 (2011)","DOI":"10.1145\/2072298.2072432"},{"key":"79_CR8","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-02282-1","volume-title":"Visual Information Retrieval using Java and LIRE","author":"M Lux","year":"2013","unstructured":"Lux, M., Oge, M.: Visual Information Retrieval using Java and LIRE. Morgan & Claypool, San Rafael (2013)"},{"issue":"4\u20133","key":"79_CR9","first-page":"142","volume":"9","author":"S Souli","year":"2012","unstructured":"Souli, S., Lachiri, Z.: Environmental sounds spectrogram classification using log-gabor filters and multiclass support vector machines. Int. J. Comput. 9(4\u20133), 142\u2013149 (2012)","journal-title":"Int. J. Comput."},{"key":"79_CR10","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 720\u2013723 (2007)"},{"key":"79_CR11","doi-asserted-by":"crossref","unstructured":"Lei, H., Meyer, B.T., Mirghafori, N.: Spectro-temporal Gabor features for speaker recognition. In: ICASSP, pp. 4241\u20134244 (2012)","DOI":"10.1109\/ICASSP.2012.6288855"},{"issue":"1","key":"79_CR12","first-page":"180","volume":"18","author":"T Gramss","year":"2014","unstructured":"Gramss, T.: Fast algorithms to find invariant features for a word recognizing neural net. Int. J. Speech Technol. 18(1), 180\u2013184 (2014)","journal-title":"Int. J. Speech Technol."},{"key":"79_CR13","doi-asserted-by":"crossref","unstructured":"Kleinschmidt, M.: Localized spectro-temporal features for automatic speech recognition, pp. 2573\u20132576 (2003)","DOI":"10.21437\/Eurospeech.2003-710"},{"issue":"3","key":"79_CR14","first-page":"416","volume":"88","author":"M Kleinschmidt","year":"2002","unstructured":"Kleinschmidt, M.: Methods for capturing spectro-temporal modulations in automatic speech recognition. Acta Acust. - Acust. 88(3), 416\u2013422 (2002)","journal-title":"Acta Acust. - Acust."},{"key":"79_CR15","doi-asserted-by":"crossref","unstructured":"Nilufar, S., Ray, N., Molla, M.K.I., Hirose, K. Spectrogram based features selection using multiple kernel learning for speech\/music discrimination. In: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 501\u2013504 (2012)","DOI":"10.1109\/ICASSP.2012.6287926"},{"issue":"2","key":"79_CR16","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1109\/LSP.2010.2100380","volume":"18","author":"J Dennis","year":"2011","unstructured":"Dennis, J., Tran, H.D., Li, H.: Spectrogram image feature for sound event classification in mismatched conditions. IEEE Signal Process. Lett. 18(2), 130\u2013133 (2011)","journal-title":"IEEE Signal Process. Lett."},{"key":"79_CR17","doi-asserted-by":"crossref","unstructured":"Ghosal, A., Chakraborty, R., Dhara, B.C., Saha, S.K.: Song\/instrumental classification using spectrogram based contextual features. In: Proceedings of the CUBE International Information Technology Conference - CUBE 2012, p. 21 (2012)","DOI":"10.1145\/2381716.2381722"},{"key":"79_CR18","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.ins.2013.04.014","volume":"243","author":"P Khunarsal","year":"2013","unstructured":"Khunarsal, P., Lursinsap, C., Raicharoen, T.: Very short time environmental sound classification based on spectrogram pattern matching. Inf. Sci. (Ny) 243, 57\u201374 (2013)","journal-title":"Inf. Sci. (Ny)"},{"key":"79_CR19","doi-asserted-by":"crossref","unstructured":"He, L., Lech, M., Maddage, N., Allen, N.: Stress and emotion recognition using log-Gabor filter analysis of speech spectrograms. In: Proceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction Work. ACII 2009, pp. 1\u20135 (2009)","DOI":"10.1109\/ACII.2009.5349454"},{"key":"79_CR20","doi-asserted-by":"crossref","unstructured":"Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The WEKA data mining software. In: ACM SIGKDD Explorations Newsletter, vol. 11, no. 1, p. 10 (2009)","DOI":"10.1145\/1656274.1656278"},{"key":"79_CR21","unstructured":"Mayo, M.: ImageFilter WEKA filter that uses LIRE to extract image features (2015). https:\/\/github.com\/mmayo888\/ImageFilter"},{"issue":"8","key":"79_CR22","doi-asserted-by":"crossref","first-page":"1727","DOI":"10.1109\/TASL.2013.2260155","volume":"21","author":"E Georganti","year":"2013","unstructured":"Georganti, E., May, T., Van De Par, S., Mourjopoulos, J.: Sound source distance estimation in rooms based on statistical properties of binaural signals. IEEE Trans. Audio, Speech Lang. Process. 21(8), 1727\u20131741 (2013)","journal-title":". IEEE Trans. Audio, Speech Lang. Process."},{"key":"79_CR23","unstructured":"Cummins, F., Grimaldi, M., Leonard, T., Simko, J.: The CHAINS speech corpus: CHAracterizing INdividual speakers. In: Proceedings of the SPECOM, pp. 1\u20136 (2006)"},{"key":"79_CR24","doi-asserted-by":"crossref","unstructured":"Chatzichristofis, S.A., Boutalis, Y.S., Arampatzis, A.: Accelerating image retrieval using Binary Haar Wavelet transform on the color and edge directivity descriptor. In: Proceedings of the 5th International Multi-Conference Computing in the Global Information Technology, ICCGI 2010, vol. 4, no. 1, pp. 41\u201347 (2010)","DOI":"10.1109\/ICCGI.2010.33"},{"key":"79_CR25","doi-asserted-by":"crossref","unstructured":"Jalab, H.: Image retrieval system based on color layout descriptor and Gabor filters. In: IEEE Conference on Open Systems, pp. 32\u201336 (2011)","DOI":"10.1109\/ICOS.2011.6079266"},{"key":"79_CR26","doi-asserted-by":"crossref","unstructured":"Chatzichristofis, S.A., Boutalis, Y.S.: FCTH: fuzzy color and texture histogram - a low level feature for accurate image retrieval. In: 2008 Ninth International Workshop on Image Analysis for Multimedia Interactive Services, pp. 191\u2013196 (2008)","DOI":"10.1109\/WIAMIS.2008.24"},{"key":"79_CR27","doi-asserted-by":"crossref","unstructured":"Bosch, A., Zisserman, A., Munoz, X.: Representing shape with a spatial pyramid kernel. In: CIVR 2007 Proceedings of the 6th ACM International Conference on Image and Video Retrieval, pp. 401\u2013408 (2007)","DOI":"10.1145\/1282280.1282340"},{"issue":"6","key":"79_CR28","first-page":"36","volume":"65","author":"R Thiruvengatanadhan","year":"2013","unstructured":"Thiruvengatanadhan, R.: Speech\/Music Classification using SVM. Int. J. Comput. Appl. 65(6), 36\u201341 (2013)","journal-title":"Int. J. Comput. Appl."},{"key":"79_CR29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1961189.1961199","volume":"2","author":"C Chang","year":"2011","unstructured":"Chang, C., Lin, C.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2, 1\u201339 (2011)","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"79_CR30","first-page":"1","volume":"7","author":"J Dem\u0161ar","year":"2006","unstructured":"Dem\u0161ar, J.: Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7, 1\u201330 (2006)","journal-title":"J. Mach. Learn. Res."},{"key":"79_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1007\/978-3-642-11509-7_7","volume-title":"Advances in Nonlinear Speech Processing","author":"I Paraskevas","year":"2010","unstructured":"Paraskevas, I., Rangoussi, M.: The hartley phase spectrum as an assistive feature for classification. In: Sol\u00e9-Casals, J., Zaiats, V. (eds.) NOLISP 2009. LNCS, vol. 5933, pp. 51\u201359. Springer, Heidelberg (2010)"},{"key":"79_CR32","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.patrec.2015.06.017","volume":"63","author":"Y Hong","year":"2015","unstructured":"Hong, Y., Zhu, W.: Spatial co-training for semi-supervised image classification. Pattern Recognit. Lett. 63, 59\u201365 (2015)","journal-title":"Pattern Recognit. Lett."}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-43958-7_79","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T16:58:52Z","timestamp":1692464332000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-43958-7_79"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319439570","9783319439587"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-43958-7_79","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}