{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T02:46:37Z","timestamp":1722912397001},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2012,3,8]],"date-time":"2012-03-08T00:00:00Z","timestamp":1331164800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2012,6]]},"DOI":"10.1007\/s10772-012-9138-4","type":"journal-article","created":{"date-parts":[[2012,3,7]],"date-time":"2012-03-07T16:53:45Z","timestamp":1331139225000},"page":"259-264","source":"Crossref","is-referenced-by-count":6,"title":["Spectral histogram of oriented gradients (SHOGs) for Tamil language male\/female speaker classification"],"prefix":"10.1007","volume":"15","author":[{"given":"A.","family":"Muthamizh Selvan","sequence":"first","affiliation":[]},{"given":"R.","family":"Rajesh","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2012,3,8]]},"reference":[{"issue":"6","key":"9138_CR1","doi-asserted-by":"crossref","first-page":"714","DOI":"10.3844\/ajassp.2008.714.720","volume":"5","author":"S. A. R. Al-Haddad","year":"2008","unstructured":"Al-Haddad, S. A. R., Samad, S. A., Hussain, A., & Ishak, K. A. (2008). Isolated Malay digit recognition using pattern recognition fusion of dynamic time warping and hidden Markov models. American Journal of Applied Sciences, 5(6), 714\u2013720.","journal-title":"American Journal of Applied Sciences"},{"issue":"3","key":"9138_CR2","first-page":"181","volume":"6","author":"M. A. Anusuya","year":"2009","unstructured":"Anusuya, M. A., & Katti, S. K. (2009). Speech recognition by machine: a review. International Journal of Computer Science and Information Security, 6(3), 181\u2013205.","journal-title":"International Journal of Computer Science and Information Security"},{"issue":"6","key":"9138_CR3","doi-asserted-by":"crossref","first-page":"1379","DOI":"10.1109\/TASL.2009.2034770","volume":"18","author":"H. Boril","year":"2010","unstructured":"Boril, H., & Hansen, J. H. L. (2010). Unsupervised equalization of Lombard effect for speech recognition in noisy adverse environments. IEEE Transactions on Audio, Speech, and Language Processing, 18(6), 1379\u20131393.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9138_CR4","first-page":"283","volume":"32","author":"M. Cherif","year":"2008","unstructured":"Cherif, M., Korba, A., Messadeg, D., Djemili, R., & Bourouba, H. (2008). Robust speech recognition using perceptual wavelet denoising and mel-frequency product spectrum cepstral coefficient features. Informatica, 32, 283\u2013288.","journal-title":"Informatica"},{"key":"9138_CR5","volume-title":"Conference on computer vision and pattern recognition (CVPR)","author":"N. Dalal","year":"2005","unstructured":"Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. In Conference on computer vision and pattern recognition (CVPR)."},{"issue":"1","key":"9138_CR6","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1109\/TASL.2006.876776","volume":"15","author":"S. Dharanipragada","year":"2007","unstructured":"Dharanipragada, S., Yapanel, U. H., & Rao, B. D. (2007). Robust feature extraction for continuous speech recognition using the MVDR spectrum estimation method. IEEE Transactions on Audio, Speech, and Language Processing, 15(1), 224\u2013234.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"1","key":"9138_CR7","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1109\/TASL.2006.876766","volume":"15","author":"J. Frankel","year":"2007","unstructured":"Frankel, J., & King, S. (2007). Speech recognition using linear dynamic models. IEEE Transactions on Audio, Speech, and Language Processing, 15(1), 246\u2013256.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"2","key":"9138_CR8","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1109\/TASL.2009.2025536","volume":"18","author":"C. Gl\u00e4ser","year":"2010","unstructured":"Gl\u00e4ser, C., Heckmann, M., Joublin, F., & Goerick, C. (2010). Combining auditory preprocessing and Bayesian estimation for robust formant tracking. IEEE Transactions on Audio, Speech, and Language Processing, 18(2), 224\u2013236.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"4","key":"9138_CR9","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1109\/89.397093","volume":"3","author":"C. R. Jankowski Jr.","year":"1995","unstructured":"Jankowski, C. R. Jr., Hoang-Doan, H. V., & Lippmann, R. P. (1995). A comparison of signal processing front ends for automatic word recognition. IEEE Transactions on Speech and Audio Processing, 3(4), 286\u2013293.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9138_CR10","doi-asserted-by":"crossref","first-page":"683","DOI":"10.1109\/ICIG.2007.53","volume-title":"Proc. IEEE fourth international conference on image and graphics","author":"H.-X. Jia","year":"2007","unstructured":"Jia, H.-X., & Zhang, Y.-J. (2007). Fast human detection by boosting histograms of oriented gradients. In Proc. IEEE fourth international conference on image and graphics (pp. 683\u2013688)."},{"key":"9138_CR11","doi-asserted-by":"crossref","DOI":"10.1186\/1687-4722-2010-651420","volume":"2010","author":"D. Kolossa","year":"2010","unstructured":"Kolossa, D., Fernandez Astudillo, R., Hoffmann, E., & Orglmeister, R. (2010). Independent component analysis and time-frequency masking for speech recognition in multitalker conditions. EURASIP Journal on Audio, Speech, and Music Processing, 2010, 651420, pp.\u00a01\u201313.","journal-title":"EURASIP Journal on Audio, Speech, and Music Processing"},{"issue":"8","key":"9138_CR12","doi-asserted-by":"crossref","first-page":"1541","DOI":"10.1109\/TASL.2008.2005345","volume":"16","author":"C.-H. Lee","year":"2008","unstructured":"Lee, C.-H., Han, C.-C., & Chuang, C.-C. (2008). Automatic classification of bird species from their sounds using two-dimensional cepstral coefficients. IEEE Transactions on Audio, Speech, and Language Processing, 16(8), 1541\u20131550.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9138_CR13","doi-asserted-by":"crossref","DOI":"10.1155\/2009\/806186","volume":"2009","author":"C. Levy","year":"2009","unstructured":"Levy, C., Linares, G., & Bonastre, J.-F. (2009). Compact acousticmodels for embedded speech recognition. EURASIP Journal on Audio, Speech, and Music Processing, 2009, 806186, pp.\u00a01\u201313.","journal-title":"EURASIP Journal on Audio, Speech, and Music Processing"},{"key":"9138_CR14","doi-asserted-by":"crossref","DOI":"10.1186\/1687-4722-2010-926951","volume":"2010","author":"A. Maier","year":"2010","unstructured":"Maier, A., Haderlein, T., Stelzle, F., Noth, E., Nkenke, E., Rosanowski,\u00a0F., Schutzenberger, A., & Schuster, M. (2010). Automatic speech recognition systems for the evaluation of voice and speech disorders in head and neck cancer. EURASIP Journal on Audio, Speech, and Music Processing, 2010, 926951, pp.\u00a01\u20137.","journal-title":"EURASIP Journal on Audio, Speech, and Music Processing"},{"issue":"4","key":"9138_CR15","doi-asserted-by":"crossref","first-page":"758","DOI":"10.1109\/TASL.2008.2012321","volume":"17","author":"N. Morales","year":"2009","unstructured":"Morales, N., Torre Toledano, D., Hansen, J. H. L., & Garrido, J. (2009). Feature compensation techniques for ASR on band-limited speech. IEEE Transactions on Audio, Speech, and Language Processing, 17(4), 758\u2013774.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"3","key":"9138_CR16","doi-asserted-by":"crossref","first-page":"640","DOI":"10.1109\/TASL.2010.2053846","volume":"19","author":"J. A. Morales-Cordovilla","year":"2011","unstructured":"Morales-Cordovilla, J. A., Peinado, A. M., S\u00e1nchez, V., & Gonz\u00e1lez, J. A. (2011). Feature extraction based on pitch-synchronous averaging for robust speech recognition. IEEE Transactions on Audio, Speech, and Language Processing, 19(3), 640\u2013651.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"3","key":"9138_CR17","first-page":"138","volume":"2","author":"L. Muda","year":"2010","unstructured":"Muda, L., Begam, M., & Elamvazuthi, I. (2010). Voice recognition algorithms using mel frequency cepstral coefficient (MFCC) and dynamic time warping (DTW) techniques. Journal of Computing, 2(3), 138\u2013143.","journal-title":"Journal of Computing"},{"key":"9138_CR18","first-page":"497","volume-title":"Proc. of international conference on advances in computing and communications (ACC 2011), Part III","author":"A. Muthamizh Selvan","year":"2011","unstructured":"Muthamizh Selvan, A., & Rajesh, R. (2011). Word classification using neural network. In Proc. of international conference on advances in computing and communications (ACC 2011), Part III (pp. 497\u2013502). Berlin: Springer. CCIS 192."},{"issue":"1","key":"9138_CR19","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1109\/TMM.2004.840604","volume":"7","author":"C. Panagiotakis","year":"2005","unstructured":"Panagiotakis, C., & Tziritas, G. (2005). A speech\/music discriminator based on RMS and zero-crossings. IEEE Transactions on Multimedia, 7(1), 155\u2013166.","journal-title":"IEEE Transactions on Multimedia"},{"key":"9138_CR20","doi-asserted-by":"crossref","DOI":"10.1155\/2009\/690451","volume":"2009","author":"H. Park","year":"2009","unstructured":"Park, H., Takiguchi, T., & Ariki, Y. (2009). Integrated phoneme subspace method for speech feature extraction. EURASIP Journal on Audio, Speech, and Music Processing, 2009, 690451, pp.\u00a01\u20136.","journal-title":"EURASIP Journal on Audio, Speech, and Music Processing"},{"issue":"5","key":"9138_CR21","doi-asserted-by":"crossref","first-page":"846","DOI":"10.1109\/TMM.2008.922870","volume":"10","author":"A. Pikrakis","year":"2008","unstructured":"Pikrakis, A., Giannakopoulos, T., & Theodoridis, S. (2008). A speech\/music discriminator of radio recordings based on dynamic programming and Bayesian networks. IEEE Transactions on Multimedia, 10(5), 846\u2013857.","journal-title":"IEEE Transactions on Multimedia"},{"key":"9138_CR22","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1109\/ICECTECH.2011.5941967","volume-title":"Proc. of 3rd international conference on electronics computer technology (ICECT)","author":"R. Rajesh","year":"2011","unstructured":"Rajesh, R., Rajeev, K., Gopakumar, V., Suchithra, K., & Lekhesh,\u00a0V.\u00a0P. (2011). On experimenting with pedestrian classification using neural network. In Proc. of 3rd international conference on electronics computer technology (ICECT) (pp. 107\u2013111)."},{"key":"9138_CR23","first-page":"1331","volume":"2","author":"E. Scheirer","year":"1997","unstructured":"Scheirer, E., & Slaney, M. (1997). Construction and evaluation of a robust multifeature speech\/music discriminator. International Conference on Acoustics, Speech, and Signal Processing Proceedings (ICASSP), 2, 1331\u20131334.","journal-title":"International Conference on Acoustics, Speech, and Signal Processing Proceedings (ICASSP)"},{"key":"9138_CR24","volume-title":"Proc. IEEE int. conference on computer vision","author":"C. Tomasi","year":"1997","unstructured":"Tomasi, C., & Manduchi, R. (1997). Bilateral filtering for gray and color images. In Proc. IEEE int. conference on computer vision."},{"issue":"1","key":"9138_CR25","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1109\/TASL.2010.2045800","volume":"19","author":"N. Wang","year":"2011","unstructured":"Wang, N., Ching, P. C., Zheng, N., & Lee, T. (2011). Robust speaker recognition using denoised vocal source and vocal tract features. IEEE Transactions on Audio, Speech, and Language Processing, 19(1), 196\u2013205.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9138_CR26","volume":"2009","author":"H. Yin","year":"2009","unstructured":"Yin, H., Nadeu, C., & Hohmann, V. (2009). Pitch and formant based order adaptation of the fractional Fourier transformand its application to speech recognition. EURASIP Journal on Audio, Speech, and Music Processing, 2009, 304579, pp.\u00a01\u201314.","journal-title":"EURASIP Journal on Audio, Speech, and Music Processing"},{"key":"9138_CR27","first-page":"4041","volume-title":"Proc. int. conference on acoustics, speech and signal processing (ICASSP)","author":"D. Yu","year":"2008","unstructured":"Yu, D., Deng, L., Droppo, J., Wu, J., Gong, Y., & Acero, A. (2008). A minimum-mean-square-error noise reduction algorithm on mel-frequency cepstra for robust speech recognition. In Proc. int. conference on acoustics, speech and signal processing (ICASSP) (pp.\u00a04041\u20134044)."},{"issue":"4","key":"9138_CR28","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1109\/89.917689","volume":"9","author":"T. Zhang","year":"2001","unstructured":"Zhang, T., & Jay Kuo, C. C. (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\/content\/pdf\/10.1007\/s10772-012-9138-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-012-9138-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-012-9138-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,31]],"date-time":"2019-05-31T00:02:44Z","timestamp":1559260964000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-012-9138-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,3,8]]},"references-count":28,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2012,6]]}},"alternative-id":["9138"],"URL":"https:\/\/doi.org\/10.1007\/s10772-012-9138-4","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,3,8]]}}}