{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T07:13:24Z","timestamp":1765610004687},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,11,7]],"date-time":"2019-11-07T00:00:00Z","timestamp":1573084800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,11,7]],"date-time":"2019-11-07T00:00:00Z","timestamp":1573084800000},"content-version":"vor","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":[[2020,3]]},"DOI":"10.1007\/s10772-019-09654-1","type":"journal-article","created":{"date-parts":[[2019,11,7]],"date-time":"2019-11-07T18:02:59Z","timestamp":1573149779000},"page":"87-100","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Improved filter bank on multitaper framework for robust Punjabi-ASR system"],"prefix":"10.1007","volume":"23","author":[{"given":"Virender","family":"Kadyan","sequence":"first","affiliation":[]},{"given":"Archana","family":"Mantri","sequence":"additional","affiliation":[]},{"given":"R. K.","family":"Aggarwal","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,11,7]]},"reference":[{"issue":"2","key":"9654_CR1","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1016\/j.specom.2012.08.007","volume":"55","author":"MJ Alam","year":"2013","unstructured":"Alam, M. J., Kinnunen, T., Kenny, P., Ouellet, P., & O\u2019Shaughnessy, D. (2013). Multitaper MFCC and PLP features for speaker verification using i-vectors. Speech Communication,55(2), 237\u2013251.","journal-title":"Speech Communication"},{"key":"9654_CR2","doi-asserted-by":"crossref","unstructured":"Charbuillet, C., Gas, B., Chetouani, M., & Zarader, J. L. (2006). Filter bank design for speaker diarization based on genetic algorithms. In 2006 IEEE international conference on acoustics, speech and signal processing, 2006. ICASSP 2006 Proceedings (Vol. 1, pp.\u00a0I\u2013I). IEEE.","DOI":"10.1109\/ICASSP.2006.1660110"},{"issue":"4","key":"9654_CR3","doi-asserted-by":"publisher","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(4), 357\u2013366.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"9654_CR4","doi-asserted-by":"publisher","DOI":"10.1515\/jisys-2017-0618","author":"M Dua","year":"2018","unstructured":"Dua, M., Aggarwal, R., & Biswas, M. (2018a). Discriminative training using noise robust integrated features and refined hmm modeling. Journal of Intelligent Systems. https:\/\/doi.org\/10.1515\/jisys-2017-0618 .","journal-title":"Journal of Intelligent Systems"},{"issue":"3","key":"9654_CR5","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1016\/j.jestch.2018.04.005","volume":"21","author":"M Dua","year":"2018","unstructured":"Dua, M., Aggarwal, R. K., & Biswas, M. (2018b). Performance evaluation of Hindi speech recognition system using optimized filterbanks. Engineering Science and Technology, an International Journal,21(3), 389\u2013398.","journal-title":"Engineering Science and Technology, an International Journal"},{"key":"9654_CR6","unstructured":"Figielska, E., & Kasprzak, W. (2008). An evolutionary programming based algorithm for HMM training. Computational Intelligence: Methods and Applications, 166\u2013175."},{"issue":"2","key":"9654_CR7","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/S0885-2308(86)80018-3","volume":"1","author":"O Ghitza","year":"1986","unstructured":"Ghitza, O. (1986). Auditory nerve representation as a front-end for speech recognition in a noisy environment. Computer Speech & Language,1(2), 109\u2013130.","journal-title":"Computer Speech & Language"},{"issue":"3","key":"9654_CR8","doi-asserted-by":"publisher","first-page":"778","DOI":"10.1109\/78.558503","volume":"45","author":"M Hansson","year":"1997","unstructured":"Hansson, M., & Salomonsson, G. (1997). A multiple window method for estimation of peaked spectra. IEEE Transactions on Signal Processing,45(3), 778\u2013781.","journal-title":"IEEE Transactions on Signal Processing"},{"key":"9654_CR9","doi-asserted-by":"crossref","unstructured":"Hansson-Sandsten, M., & Sandberg, J. (2009). Optimal cepstrum estimation using multiple windows. In IEEE international conference on acoustics, speech and signal processing, 2009. ICASSP 2009. (pp.\u00a03077\u20133080). IEEE.","DOI":"10.1109\/ICASSP.2009.4960274"},{"issue":"1","key":"9654_CR10","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1109\/PROC.1978.10837","volume":"66","author":"FJ Harris","year":"1978","unstructured":"Harris, F. J. (1978). On the use of windows for harmonic analysis with the discrete Fourier transform. Proceedings of the IEEE,66(1), 51\u201383.","journal-title":"Proceedings of the IEEE"},{"issue":"1","key":"9654_CR11","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1109\/TSA.2003.819949","volume":"12","author":"Y Hu","year":"2004","unstructured":"Hu, Y., & Loizou, P. C. (2004). Speech enhancement based on wavelet thresholding the multitaper spectrum. IEEE Transactions on Speech and Audio Processing,12(1), 59\u201367.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9654_CR12","doi-asserted-by":"crossref","unstructured":"Hung, J. W. (2004). Optimization of filter-bank to improve the extraction of MFCC features in speech recognition. In Proceedings of 2004 international symposium on intelligent multimedia, video and speech processing, 2004 (pp.\u00a0675\u2013678). IEEE","DOI":"10.1109\/ISIMP.2004.1434154"},{"key":"9654_CR13","doi-asserted-by":"crossref","unstructured":"Hung, J. W. (2004). Optimization of filter bank to improve the extraction of MFCC features in speech recognition. In Proceedings of International Symposium on Intelligent Multimedia, Video and Speech Processing, 2004. (pp. 675\u2013678).","DOI":"10.1109\/ISIMP.2004.1434154"},{"issue":"5","key":"9654_CR14","first-page":"1","volume":"64","author":"V Kadyan","year":"2017","unstructured":"Kadyan, V., Mantri, A., & Aggarwal, R. K. (2017a). Refinement of HMM model parameters for punjabi automatic speech recognition (PASR) system. IETE Journal of Research,64(5), 1\u201316.","journal-title":"IETE Journal of Research"},{"issue":"4","key":"9654_CR15","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1007\/s10772-017-9446-9","volume":"20","author":"V Kadyan","year":"2017","unstructured":"Kadyan, V., Mantri, A., & Aggarwal, R. K. (2017b). A heterogeneous speech feature vectors generation approach with hybrid hmm classifiers. International Journal of Speech Technology,20(4), 761\u2013769.","journal-title":"International Journal of Speech Technology"},{"key":"9654_CR16","doi-asserted-by":"crossref","unstructured":"Kinnunen, T., Saeidi, R., Sandberg, J., & Hansson-Sandsten, M. (2010). What else is new than the Hamming window? Robust MFCCs for speaker recognition via multitapering. In Eleventh Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2010-724"},{"issue":"2","key":"9654_CR17","doi-asserted-by":"publisher","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. S. (2001). Optimisation of HMM topology and its model parameters by genetic algorithms. Pattern Recognition,34(2), 509\u2013522.","journal-title":"Pattern Recognition"},{"key":"9654_CR18","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. In IEEE workshop on Automatic speech recognition and understanding, 2001. ASRU\u201901 (pp.\u00a049\u201352). IEEE."},{"key":"9654_CR19","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. In IEEE workshop on automatic speech recognition and understanding, 2001. ASRU\u201901. (pp. 49\u201352)."},{"key":"9654_CR20","doi-asserted-by":"crossref","unstructured":"Maganti, H. K., &Matassoni, M. (2010). An auditory based modulation spectral feature for reverberant speech recognition. In Eleventh Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2010-225"},{"key":"9654_CR21","doi-asserted-by":"crossref","unstructured":"Maldonado, Y. P., Morales, S. O. C., & Ortega, R. O. C. (2012). GA approaches to HMM optimization for automatic speech recognition. In Mexican conference on pattern recognition (pp. 313\u2013322). Springer, Berlin.","DOI":"10.1007\/978-3-642-31149-9_32"},{"key":"9654_CR22","unstructured":"Minh, V. D., & Lee, S. (2004). PCA-based human auditory filter bank for speech recognition. In 2004 International Conference on Signal Processing and Communications, 2004. SPCOM\u201904 (pp.\u00a0393\u2013397). IEEE."},{"key":"9654_CR23","unstructured":"Patterson, R. D., Nimmo-Smith, I., Holdsworth, J., & Rice, P. (1987). An efficient auditory filter bank based on the gammatone function. In A meeting of the IOC Speech Group on Auditory Modelling at RSRE (Vol. 2, No. 7)."},{"key":"9654_CR24","doi-asserted-by":"crossref","unstructured":"Pinheiro, H. N., Neto, F. M., Oliveira, A. L., Ren, T. I., Cavalcanti, G. D., & Adami, A. G. (2017). Optimizing speaker-specific filter banks for speaker verification. In 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp.\u00a05350\u20135354). IEEE.","DOI":"10.1109\/ICASSP.2017.7953178"},{"key":"9654_CR25","volume-title":"Fundamentals of speech recognition","author":"LR Rabiner","year":"1993","unstructured":"Rabiner, L. R., & Juang, B. H. (1993). Fundamentals of speech recognition (Vol. 14). Englewood Cliffs: PTR Prentice Hall."},{"issue":"1","key":"9654_CR26","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1109\/78.365298","volume":"43","author":"KS Riedel","year":"1995","unstructured":"Riedel, K. S., & Sidorenko, A. (1995). Minimum bias multiple taper spectral estimation. IEEE Transactions on Signal Processing,43(1), 188\u2013195.","journal-title":"IEEE Transactions on Signal Processing"},{"issue":"4","key":"9654_CR27","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1109\/LSP.2010.2040228","volume":"17","author":"J Sandberg","year":"2010","unstructured":"Sandberg, J., Hansson-Sandsten, M., Kinnunen, T., Saeidi, R., Flandrin, P., & Borgnat, P. (2010). Multitaper estimation of frequency-warped cepstra with application to speaker verification. IEEE Signal Processing Letters,17(4), 343\u2013346.","journal-title":"IEEE Signal Processing Letters"},{"key":"9654_CR28","doi-asserted-by":"crossref","unstructured":"Schluter, R., Bezrukov, I., Wagner, H., & Ney, H. (2007). Gammatone features and feature combination for large vocabulary speech recognition. In IEEE International Conference on Acoustics, Speech and Signal Processing, 2007. ICASSP 2007 (Vol. 4, pp. IV\u2013649). IEEE.","DOI":"10.1109\/ICASSP.2007.366996"},{"issue":"9","key":"9654_CR29","doi-asserted-by":"publisher","first-page":"1055","DOI":"10.1109\/PROC.1982.12433","volume":"70","author":"DJ Thomson","year":"1982","unstructured":"Thomson, D. J. (1982). Spectrum estimation and harmonic analysis. Proceedings of the IEEE,70(9), 1055\u20131096.","journal-title":"Proceedings of the IEEE"},{"key":"9654_CR30","doi-asserted-by":"crossref","unstructured":"Yang, F., Zhang, C., & Bai, G. (2008). A novel genetic algorithm based on tabu search for HMM optimization. In Natural Computation, 2008. ICNC\u201908. Fourth International Conference on (Vol. 4, pp. 57\u201361). IEEE.","DOI":"10.1109\/ICNC.2008.365"},{"key":"9654_CR31","doi-asserted-by":"crossref","unstructured":"Yang, F., Zhang, C., & Sun, T. (2008, December). Comparison of particle swarm optimization and genetic algorithm for HMM training. In 19th IEEE International conference on pattern recognition, 2008. ICPR 2008. (pp.\u00a01\u20134).","DOI":"10.1109\/ICPR.2008.4761282"},{"issue":"6","key":"9654_CR32","doi-asserted-by":"publisher","first-page":"514","DOI":"10.1016\/j.specom.2007.04.005","volume":"49","author":"A Zolnay","year":"2007","unstructured":"Zolnay, A., Kocharov, D., Schl\u00fcter, R., & Ney, H. (2007). Using multiple acoustic feature sets for speech recognition. Speech Communication,49(6), 514\u2013525.","journal-title":"Speech Communication"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-019-09654-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-019-09654-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-019-09654-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,3]],"date-time":"2022-10-03T23:03:46Z","timestamp":1664838226000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-019-09654-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11,7]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,3]]}},"alternative-id":["9654"],"URL":"https:\/\/doi.org\/10.1007\/s10772-019-09654-1","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,11,7]]},"assertion":[{"value":"24 May 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 October 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 November 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}