{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T15:10:30Z","timestamp":1758121830158},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2014,8,7]],"date-time":"2014-08-07T00:00:00Z","timestamp":1407369600000},"content-version":"tdm","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":[[2015,3]]},"DOI":"10.1007\/s10772-014-9246-4","type":"journal-article","created":{"date-parts":[[2014,8,6]],"date-time":"2014-08-06T15:37:16Z","timestamp":1407339436000},"page":"1-16","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Selection and enhancement of Gabor filters for automatic speech recognition"],"prefix":"10.1007","volume":"18","author":[{"given":"Gy\u00f6rgy","family":"Kov\u00e1cs","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"L\u00e1szl\u00f3","family":"T\u00f3th","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dirk","family":"Van Compernolle","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,8,7]]},"reference":[{"issue":"2","key":"9246_CR1","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1007\/BF00336731","volume":"42","author":"AM Aertsen","year":"1981","unstructured":"Aertsen, A. M., & Johannesma, P. I. (1981). The spectro-temporal receptive field. A functional characteristic of auditory neurons. Biological Cybernetics, 42(2), 133\u2013143.","journal-title":"Biological Cybernetics"},{"key":"9246_CR2","doi-asserted-by":"crossref","unstructured":"Abdel-Hamid, O., Mohamed, A., Jiang, H., & Penn, G. (2012). Applying Convolutional Neural Networks concepts to hybrid NN-HMM model for speech recognition. Proceedings of ICASSP, 2012, pp. 4277\u20134280.","DOI":"10.1109\/ICASSP.2012.6288864"},{"key":"9246_CR3","doi-asserted-by":"crossref","unstructured":"Biem, A., Mcdermott, E., & Katagiri, S. (1995). A discriminative filter bank model for speech recognition. Proceedings of ICASSP-96, pp. 545\u2013548.","DOI":"10.21437\/Eurospeech.1995-140"},{"key":"9246_CR4","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4615-3210-1","volume-title":"Connectionist speech recognition: A hybrid approach","author":"H Bourlard","year":"1994","unstructured":"Bourlard, H., & Morgan, N. (1994). Connectionist speech recognition: A hybrid approach. Boston: Kluwer Academic Publication."},{"key":"9246_CR5","doi-asserted-by":"crossref","unstructured":"Ezzat, T., Bouvrie, J., & Poggio, T. (2007). Spectro-temporal analysis of speech using 2-D Gabor filters. Proceedings of interspeech, pp. 50\u2013509.","DOI":"10.21437\/Interspeech.2007-236"},{"key":"9246_CR6","first-page":"429","volume":"93","author":"D G\u00e1bor","year":"1946","unstructured":"G\u00e1bor, D. (1946). Theory of communication. Journal of IEE, 93, 429\u2013457.","journal-title":"Journal of IEE"},{"key":"9246_CR7","unstructured":"Gelbart, D., Kleinschmidt, M., & Meyer, B. T. (2013). Gabor feature extraction for automatic speech recognition. Retrieved October 22, 2013, from http:\/\/www1.icsi.berkeley.edu\/Speech\/papers\/gabor\/ ."},{"key":"9246_CR8","unstructured":"Gosztolya, G., & T\u00f3th, L. (2010). Keyword spotting experiments on broadcast news data using phone-based technologies (in Hungarian). Proceedings of MSZNY, pp. 224\u2013235."},{"key":"9246_CR9","unstructured":"Gramss, T. (1991). Fast algorithms to find invariant features for a word recognizing neural net. Proceedings of second international conference on artificial neural networks, pp. 180\u2013184."},{"key":"9246_CR10","unstructured":"Hirsch, H.-G. (2010). FaNT: Filtering and noise-adding tool. Retrieved March 22, 2010, from http:\/\/dnt.kr.hs-niederrhein.de\/download.html ."},{"key":"9246_CR11","unstructured":"Huang, G.-B., Zhu, Q.-Y., & Siew, C.-K. (2006). Extreme learning machine: A new learning scheme of feedforward neural networks. Proceedings of international joint conference on neural netwroks, pp. 985\u2013990."},{"issue":"11","key":"9246_CR12","doi-asserted-by":"crossref","first-page":"1641","DOI":"10.1016\/j.patrec.2005.01.015","volume":"26","author":"L-L Huang","year":"2005","unstructured":"Huang, L.-L., Shimizu, A., & Kobatake, H. (2005). Robust face detection using Gabor filter features. Pattern Recognition Letters, 26(11), 1641\u20131649.","journal-title":"Pattern Recognition Letters"},{"key":"9246_CR13","doi-asserted-by":"crossref","unstructured":"Jaitly, N., & Hinton, G. (2011). Learning a better representation of speech soundwaves using restricted boltzmann machines. Proceedings of ICASSP, 2011, pp. 5884\u20135887.","DOI":"10.1109\/ICASSP.2011.5947700"},{"issue":"6","key":"9246_CR14","doi-asserted-by":"crossref","first-page":"1233","DOI":"10.1152\/jn.1987.58.6.1233","volume":"56","author":"JP Jones","year":"1987","unstructured":"Jones, J. P., & Palmer, L. A. (1987). An evaluation of two-dimensional Gabor filter model of simple receptive fields in cat striate cortex. Journal of Neurophisiology, 56(6), 1233\u20131258.","journal-title":"Journal of Neurophisiology"},{"issue":"1","key":"9246_CR15","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/S0167-6393(99)00002-3","volume":"28","author":"N Kanedera","year":"1999","unstructured":"Kanedera, N., Arai, T., Hermansky, H., & Pavel, M. (1999). On the relative importance of various components of the modulation spectrum for automatic speech recognition. Speech Communication, 28(1), 43\u201355.","journal-title":"Speech Communication"},{"issue":"3","key":"9246_CR16","first-page":"416","volume":"88","author":"M Kleinschmidt","year":"2002","unstructured":"Kleinschmidt, M. (2002a). Methods for capturing spectro-temporal modulations in automatic speech recognition. Acta Acustica united with Acustica, 88(3), 416\u2013422.","journal-title":"Acta Acustica united with Acustica"},{"key":"9246_CR17","doi-asserted-by":"crossref","unstructured":"Kleinschmidt, M. (2002b). Spectro-temporal Gabor features as a front end for automatic speech recognition. Proceedings of triennial forum acusticum, September, 2002, Seville.","DOI":"10.21437\/Eurospeech.2003-710"},{"key":"9246_CR18","doi-asserted-by":"crossref","unstructured":"Kleinschmidt, M., & Gelbart, D. (2002). Improving word accuracy with Gabor feature extraction. Proceedings of ICSLP, pp. 25\u201328.","DOI":"10.21437\/ICSLP.2002-5"},{"key":"9246_CR19","doi-asserted-by":"crossref","unstructured":"Kov\u00e1cs, G., & T\u00f3th, L. (2010). Localized spectro-temporal features for noise-robust speech recognition. Proceedings of ICCC-CONTI, pp. 481\u2013485.","DOI":"10.1109\/ICCCYB.2010.5491225"},{"key":"9246_CR20","doi-asserted-by":"crossref","unstructured":"Kov\u00e1cs, G., & T\u00f3th, L. (2011). Phone recognition experiments with 2D DCT spectro-temporal features. Proceedings of SACI, 2011, pp. 143\u2013146.","DOI":"10.1109\/SACI.2011.5872988"},{"key":"9246_CR21","doi-asserted-by":"crossref","unstructured":"Kov\u00e1cs, G., & T\u00f3th, L. (2013). The joint optimization of spectro-temporal features and neural net classifiers. Proceedings of TSD, 2013, pp. 552\u2013559.","DOI":"10.1007\/978-3-642-40585-3_69"},{"key":"9246_CR22","unstructured":"Lamel, L. F., Kassel, R., & Seneff, S. (1986). Speech database development: Design and analysis of the acoustic-phonetic corpus. Proceedings of DARPA speech recognition workshop, pp. 100\u2013109."},{"key":"9246_CR23","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1109\/TSA.2002.805644","volume":"11","author":"C Lee","year":"2003","unstructured":"Lee, C., Hyun, D., Choi, E., & Go, J. (2003). Optimizing feature extraction for speech recognition. IEEE Transactions on Speech and Audio Processing, 11, 80\u201387.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9246_CR24","doi-asserted-by":"crossref","first-page":"1641","DOI":"10.1109\/29.46546","volume":"37","author":"KF Lee","year":"1989","unstructured":"Lee, K. F., & Hon, H. W. (1989). Speaker-independent phone recognition using Hidden Markov models. IEEE Transactions on Acoustics Speech and Signal Processing, 37, 1641\u20131648.","journal-title":"IEEE Transactions on Acoustics Speech and Signal Processing"},{"key":"9246_CR25","unstructured":"Lee, S.-M., Fang, S.-H., Hung, J.-W., & Lee L.-S. (2001). Improved MFCC feature extraction by PCA-optimized filter-bank for speech recognition. IEEE workshop on automatic speech recognition and understanding, ASRU \u201901, pp. 49\u201352."},{"key":"9246_CR26","doi-asserted-by":"crossref","unstructured":"Meyer, B. T., & Kollmeier, B. (2008). Optimization and evaluation of Gabor feature sets for ASR. Proceedings of interspeech, pp. 906\u2013909.","DOI":"10.21437\/Interspeech.2008-211"},{"issue":"1","key":"9246_CR27","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1109\/TASL.2011.2109382","volume":"20","author":"A Mohamed","year":"2012","unstructured":"Mohamed, A., Dahl, G. E., & Hinton, G. (2012). Acoustic modeling using deep belief networks. IEEE Transactions on Audio, Speech, and Language Processing, 20(1), 14\u201322.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9246_CR28","unstructured":"Palaz, D., Collobert, R., & Magimai-Doss, M. (2013). End-to-end phoneme sequence recognition using convolutional neural networks. NIPS deep learning workshop."},{"key":"9246_CR29","doi-asserted-by":"crossref","unstructured":"Sainath, T. N., Kingsbury, A., Ramebhadran, B., & Ramebhadran, M. (2013). Learning filter banks within a deep neural network. Proceedings of ASRU 2013.","DOI":"10.1109\/ASRU.2013.6707746"},{"key":"9246_CR30","doi-asserted-by":"crossref","first-page":"4134","DOI":"10.1121\/1.3699200","volume":"132","author":"MR Sch\u00e4dler","year":"2012","unstructured":"Sch\u00e4dler, M. R., Meyer, B. T., & Kollmeier, B. (2012). Spectro-temporal modulation subspace-spanning filter bank features for robuest automatic speech recognition. The Journal of Acoustical Society of America, 132, 4134\u20134151.","journal-title":"The Journal of Acoustical Society of America"},{"key":"9246_CR31","first-page":"76","volume-title":"Pattern recognition recent advances","author":"P Somol","year":"2010","unstructured":"Somol, P., Novovicova, J., & Pudil, P. (2010). Efficient feature subset selection and subset size optimization. In E. Herout (Ed.), Pattern recognition recent advances (pp. 76\u201398). Rijeka: InTech."},{"key":"9246_CR32","doi-asserted-by":"crossref","unstructured":"Sun, Z., Bebis, G., & Miller, R. (2003). Evolutionary Gabor filter optimization with application to vehicle detection. Proceedings of ICDM, pp. 307\u2013314.","DOI":"10.1109\/ICDM.2003.1250934"},{"key":"9246_CR33","unstructured":"Tasi, D. M. (2009). Optimal Gabor filter design for texture segmentation using stochastic optimization. Image and Vision Computing, 19, 299\u2013316."},{"key":"9246_CR34","doi-asserted-by":"crossref","unstructured":"Tiitinen, H., Miettinen, I., Alku, P., & May, P. (2012). Transient and sustained cortical activity elicited by connected speech of varying intelligibility. BMC Neuroscience, 13, 157.","DOI":"10.1186\/1471-2202-13-157"},{"key":"9246_CR35","doi-asserted-by":"crossref","unstructured":"T\u00f3th, L. (2013). Convolutional deep rectifier neural nets for phone recognition. Proceedings of interspeech, 2013, pp. 1722\u20131726.","DOI":"10.21437\/Interspeech.2013-429"},{"issue":"3","key":"9246_CR36","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","volume":"12","author":"A Varga","year":"1993","unstructured":"Varga, A., & Steeneken, H. (1993). Assessment for automatic speech recognition: II. NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systems. Speech Communication, 12(3), 247\u2013251.","journal-title":"Speech Communication"},{"key":"9246_CR37","doi-asserted-by":"crossref","unstructured":"Vesely, K., Karafiat, M., & Grezl, F. (2011). Convolutive bottleneck network features for LVCSR. Proceedings of ASRU, 2011, pp. 42\u201347.","DOI":"10.1109\/ASRU.2011.6163903"},{"key":"9246_CR38","unstructured":"Vinyals, O., & Deng, L. (2012). Are sparse representations rich enough for acoustic modeling? Proceedings of interspeech, 2012, pp. 1\u20131."},{"key":"9246_CR39","unstructured":"von Ossietzky, C. (2013). Gabor filter bank features. Retrieved September 15, 2013, from http:\/\/medi.uni-oldenburg.de\/GBFB ."},{"key":"9246_CR40","volume-title":"The HTK book version 3.4","author":"SJ Young","year":"2006","unstructured":"Young, S. J., Evermann, G., Gales, M. J. F., Kershaw, D., Moore, G., Odell, J. J., et al. (2006). The HTK book version 3.4. Cambridge: Cambridge University Engineering Department."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-014-9246-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-014-9246-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-014-9246-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,15]],"date-time":"2023-07-15T19:30:52Z","timestamp":1689449452000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-014-9246-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,8,7]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2015,3]]}},"alternative-id":["9246"],"URL":"https:\/\/doi.org\/10.1007\/s10772-014-9246-4","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,8,7]]}}}