{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T04:55:31Z","timestamp":1764996931794},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2012,2,9]],"date-time":"2012-02-09T00:00:00Z","timestamp":1328745600000},"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\/s10772-012-9133-9","type":"journal-article","created":{"date-parts":[[2012,2,8]],"date-time":"2012-02-08T08:05:26Z","timestamp":1328688326000},"page":"191-201","source":"Crossref","is-referenced-by-count":22,"title":["Filterbank optimization for robust ASR using GA and PSO"],"prefix":"10.1007","volume":"15","author":[{"given":"R. K.","family":"Aggarwal","sequence":"first","affiliation":[]},{"given":"M.","family":"Dave","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2012,2,9]]},"reference":[{"key":"9133_CR1","author":"R. K. Aggarwal","year":"2011","unstructured":"Aggarwal, R. K., & Dave, M. (2011a). Performance evaluation of sequentially combined heterogeneous feature streams for Hindi speech recognition system. Telecommunication Systems Journal. doi: 10.1007\/s11235-011-9623-0 . Special issue on signal processing applications in human computer interaction.","journal-title":"Telecommunication Systems Journal"},{"issue":"4","key":"9133_CR2","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1007\/s10772-011-9108-2","volume":"14","author":"R. K. Aggarwal","year":"2011","unstructured":"Aggarwal, R. K., & Dave, M. (2011b). Acoustic modeling problem for automatic speech recognition system: conventional methods (Part\u00a0I). International Journal of Speech Technology, 14(4), 297\u2013308.","journal-title":"International Journal of Speech Technology"},{"issue":"4","key":"9133_CR3","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1007\/s10772-011-9106-4","volume":"14","author":"R. K. Aggarwal","year":"2011","unstructured":"Aggarwal, R. K., & Dave, M. (2011c). Acoustic modeling problem for automatic speech recognition system: advances and refinements (Part\u00a0II). International Journal of Speech Technology, 14(4), 309\u2013320.","journal-title":"International Journal of Speech Technology"},{"key":"9133_CR4","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-49127-9","volume-title":"Handbook of speech processing","author":"J. Benesty","year":"2008","unstructured":"Benesty, J., Sondhi, M.M., & Huang, Y. (2008). Handbook of speech processing. Berlin: Springer."},{"key":"9133_CR5","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1109\/TASSP.1979.1163209","volume":"27","author":"S. F. Boll","year":"1979","unstructured":"Boll, S. F. (1979). Suppression of acoustic noise in speech using spectral subtraction. IEEE Transactions on Acoustics, Speech, and Signal Processing, 27, 113\u2013120.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"9133_CR6","series-title":"Lecture notes in computer science","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1007\/3-540-44805-5_40","volume-title":"Text, speech and dialogue","author":"L. Burget","year":"2001","unstructured":"Burget, L., & Hermansky, H. (2001). Data driven design of filterbank for speech recognition. In Lecture notes in computer science: Vol. 2166. Text, speech and dialogue (pp. 299\u2013304). Berlin: Springer."},{"key":"9133_CR7","first-page":"1727","volume-title":"Proceedings of IEEE international conference on acoustics, speech, and signal processing","author":"C. W. Chau","year":"1997","unstructured":"Chau, C. W., Kwong, S., Diu, C. K., & Fahrner, W. R. (1997). Optimization of HMM by a genetic algorithm. In Proceedings of IEEE international conference on acoustics, speech, and signal processing (pp. 1727\u20131730)."},{"issue":"4","key":"9133_CR8","doi-asserted-by":"crossref","first-page":"1218","DOI":"10.1109\/TSA.2005.860851","volume":"14","author":"J. Chen","year":"2006","unstructured":"Chen, J., Benesty, J., Huang, Y., & Doclo, S. (2006). New insights into the noise reduction Wiener filter. IEEE Transactions on Audio, Speech, & Language Processing, 14(4), 1218\u20131234.","journal-title":"IEEE Transactions on Audio, Speech, & Language Processing"},{"key":"9133_CR9","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"S. Davis","year":"1980","unstructured":"Davis, S., & Mermelstein, P. (1980). Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Transactions on Acoustics, Speech, and Signal Processing, 28, 357\u2013366.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"issue":"1","key":"9133_CR10","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1109\/4235.585892","volume":"1","author":"M. Dorigo","year":"1997","unstructured":"Dorigo, M., & Gambardella, L. M. (1997). Ant colony system: a\u00a0cooperative learning approach to the traveling salesman problem. IEEE Transactions on Evolutionary Computation, 1(1), 53\u201356.","journal-title":"IEEE Transactions on Evolutionary Computation"},{"issue":"5","key":"9133_CR11","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1109\/89.536929","volume":"4","author":"M. Gales","year":"1996","unstructured":"Gales, M., & Young, S. (1996). Robust continuous speech recognition using parallel model combination. IEEE Transactions on Speech and Audio Processing, 4(5), 352\u2013359.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9133_CR12","doi-asserted-by":"crossref","first-page":"1738","DOI":"10.1121\/1.399423","volume":"87","author":"H. Hermansky","year":"1990","unstructured":"Hermansky, H. (1990). Perceptually predictive (PLP) analysis of speech. The Journal of the Acoustical Society of America, 87, 1738\u20131752.","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"4","key":"9133_CR13","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1109\/89.326616","volume":"2","author":"H. Hermansky","year":"1994","unstructured":"Hermansky, H., & Morgan, N. (1994). RASTA processing of speech. IEEE Transactions on Speech and Audio Processing, 2(4), 578\u2013589.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9133_CR14","volume-title":"Adaptation in natural and artificial systems","author":"J. H. Holland","year":"1975","unstructured":"Holland, J. H. (1975). Adaptation in natural and artificial systems. Ann Arbor: University of Michigan Press."},{"key":"9133_CR15","doi-asserted-by":"crossref","first-page":"1942","DOI":"10.1109\/ICNN.1995.488968","volume-title":"Proceedings of international conference on neural networks","author":"J. Kennedy","year":"1995","unstructured":"Kennedy, J., & Eberhart, R. C. (1995). Particle swarm optimization. In Proceedings of international conference on neural networks (pp.\u00a01942\u20131948). Piscataway: IEEE."},{"key":"9133_CR16","volume-title":"Swarm intelligence","author":"J. Kennedy","year":"2001","unstructured":"Kennedy, J., Eberhart, R.C., & Shi, Y. (2001). Swarm intelligence. San Mateo: Morgan Kaufmann."},{"key":"9133_CR17","first-page":"421","volume-title":"Proceedings IEEE international conference on acoustics, speech and signal processing","author":"J. Koehler","year":"1994","unstructured":"Koehler, J., Morgan, N., Hermansky, H., Hirsch, H. G., & Tong, G. (1994). Integrating RASTA-PLP into speech recognition. In Proceedings IEEE international conference on acoustics, speech and signal processing (Vol.\u00a01, pp. 421\u2013424)."},{"issue":"5","key":"9133_CR18","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1109\/41.538613","volume":"43","author":"S. Kwong","year":"1996","unstructured":"Kwong, S., Chau, C. W., & Halang, W. A. (1996). Genetic algorithm for optimizing the nonlinear time alignment of automatic speech recognition systems. IEEE Transactions on Industrial Electronics, 43(5), 559\u2013566.","journal-title":"IEEE Transactions on Industrial Electronics"},{"issue":"2","key":"9133_CR19","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1016\/S0031-3203(99)00226-5","volume":"34","author":"S. Kwong","year":"2001","unstructured":"Kwong, S., Chau, C. W., Man, K. F., & Tang, K.\u00a0S. (2001). Optimization of HMM topology and its model parameters by genetic algorithms. Pattern Recognition, 34(2), 509\u2013522.","journal-title":"Pattern Recognition"},{"key":"9133_CR20","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1016\/S0165-1684(02)00138-X","volume":"82","author":"S. Kwong","year":"2002","unstructured":"Kwong, S., He, Q. H., Ku, K. W., Chan, T. M., Man, K. F., & Tang, K.\u00a0S. (2002). A genetic classification error method for speech recognition. Signal Processing, 82, 737\u2013748.","journal-title":"Signal Processing"},{"issue":"6","key":"9133_CR21","doi-asserted-by":"crossref","first-page":"430","DOI":"10.1109\/89.544528","volume":"4","author":"P. C. Loizou","year":"1996","unstructured":"Loizou, P. C., & Spanias, A. S. (1996). High-performance alphabet recognition. IEEE Transactions on Speech and Audio Processing, 4(6), 430\u2013445.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9133_CR22","doi-asserted-by":"crossref","first-page":"1910","DOI":"10.1016\/j.mcm.2010.03.041","volume":"52","author":"N. Najkar","year":"2010","unstructured":"Najkar, N., Razzazi, F., & Sameti, H. (2010). A novel approach to HMM-based speech recognition systems using particle swarm optimization. Mathematical and Computer Modelling, 52, 1910\u20131920.","journal-title":"Mathematical and Computer Modelling"},{"key":"9133_CR23","first-page":"177","volume-title":"Proceedings IEEE ICASSP","author":"K. K. Paliwal","year":"1987","unstructured":"Paliwal, K. K. (1987). A speech enhancement method based on Kalman filtering. In Proceedings IEEE ICASSP (pp. 177\u2013180)."},{"key":"9133_CR24","series-title":"Studies in computational intelligence","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1007\/978-3-642-00267-0_12","volume-title":"Nature-inspired algorithms for optimization","author":"P. Rabanal","year":"2009","unstructured":"Rabanal, P., Rodriguez, I., & Rubio, F. (2009). Applying river formation dynamics to solve NP-complete problems. In Studies in computational intelligence: Vol. 193. Nature-inspired algorithms for optimization (pp. 333\u2013368). Springer, Berlin."},{"issue":"2","key":"9133_CR25","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"L. R. Rabiner","year":"1989","unstructured":"Rabiner, L. R. (1989). A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2), 257\u2013286.","journal-title":"Proceedings of the IEEE"},{"key":"9133_CR26","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1016\/j.csl.2006.06.003","volume":"21","author":"K. S. Rao","year":"2007","unstructured":"Rao, K. S., & Yegnanarayana, B. (2007). Modeling durations of syllables using neural networks. Computer Speech and Language, 21, 282\u2013295.","journal-title":"Computer Speech and Language"},{"issue":"5","key":"9133_CR27","doi-asserted-by":"crossref","first-page":"783","DOI":"10.1007\/s12046-011-0047-z","volume":"36","author":"K. S. Rao","year":"2011","unstructured":"Rao, K. S. (2011). Role of neural network models for developing speech systems. Sadhana, 36(5), 783\u2013836.","journal-title":"Sadhana"},{"key":"9133_CR28","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1007\/BFb0040810","volume-title":"Proceedings of seventh annual conference on evolutionary programming","author":"Y. Shi","year":"1998","unstructured":"Shi, Y., & Eberhart, R. C. (1998). Parameter selection in particle swarm optimization. In Proceedings of seventh annual conference on evolutionary programming (pp. 591\u2013601)."},{"key":"9133_CR29","first-page":"281","volume-title":"Proceedings of the IEEE international symposium on circuits and systems (ISCAS\u201903)","author":"M. D. Skowronski","year":"2003","unstructured":"Skowronski, M. D., & Harris, J. G. (2003). Improving the filterbank of a classic speech feature extraction algorithm. In Proceedings of the IEEE international symposium on circuits and systems (ISCAS\u201903), (Vol.\u00a04, pp. 281\u2013284)."},{"issue":"3","key":"9133_CR30","doi-asserted-by":"crossref","first-page":"1774","DOI":"10.1121\/1.1777872","volume":"116","author":"M. D. Skowronski","year":"2004","unstructured":"Skowronski, M. D., & Harris, J. G. (2004). Exploiting independent filter bandwidth of human factor cepstral coefficients in automatic speech recognition. The Journal of the Acoustical Society of America, 116(3), 1774\u20131780.","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"2","key":"9133_CR31","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1109\/TEVC.2007.896686","volume":"12","author":"Y.\u00a0D. Valle","year":"2008","unstructured":"Valle, Y.\u00a0D., Venayagamoorthy, G.\u00a0K., Mohagheghi, S., Hernandez, J.-C., & Harley, R.\u00a0G. (2008). Particle swarm optimization: basic concepts, variants and applications in power systems. IEEE Transactions on Evolutionary Computation, 12(2), 171\u2013195.","journal-title":"IEEE Transactions on Evolutionary Computation"},{"issue":"3","key":"9133_CR32","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. J. M. (1993). Assessment for automatic recognition: II. NOISEX-92: a\u00a0database and an experiment to study the effect of additive noise on speech recognition systems. ESCA Journal of Speech Communication, 12(3), 247\u2013251.","journal-title":"ESCA Journal of Speech Communication"},{"issue":"4","key":"9133_CR33","first-page":"10","volume":"53","author":"L. R. Welch","year":"2003","unstructured":"Welch, L. R. (2003). HMMs and the Baum-Welch algorithms. IEEE Information Theory Society Newsletter, 53(4), 10\u201313.","journal-title":"IEEE Information Theory Society Newsletter"},{"issue":"6","key":"9133_CR34","doi-asserted-by":"crossref","first-page":"582","DOI":"10.1007\/BF02943243","volume":"16","author":"F. Zheng","year":"2001","unstructured":"Zheng, F., Zhang, G., & Song, Z. (2001). Comparison of different implementations of MFCC. Journal of Computer Science and Technology, 16(6), 582\u2013589.","journal-title":"Journal of Computer Science and Technology"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-012-9133-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-012-9133-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-012-9133-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,30]],"date-time":"2019-05-30T20:02:44Z","timestamp":1559246564000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-012-9133-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,2,9]]},"references-count":34,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2012,6]]}},"alternative-id":["9133"],"URL":"https:\/\/doi.org\/10.1007\/s10772-012-9133-9","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,2,9]]}}}