{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T06:49:08Z","timestamp":1765176548774,"version":"3.37.3"},"reference-count":82,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T00:00:00Z","timestamp":1558310400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T00:00:00Z","timestamp":1558310400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61503264"],"award-info":[{"award-number":["61503264"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2019,8]]},"DOI":"10.1007\/s00034-019-01141-x","type":"journal-article","created":{"date-parts":[[2019,5,21]],"date-time":"2019-05-21T10:52:17Z","timestamp":1558435937000},"page":"3521-3547","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Automatic Hypernasality Detection in Cleft Palate Speech Using CNN"],"prefix":"10.1007","volume":"38","author":[{"given":"Xiyue","family":"Wang","sequence":"first","affiliation":[]},{"given":"Ming","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Sen","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Heng","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Hua","family":"Huang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7168-2737","authenticated-orcid":false,"given":"Ling","family":"He","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,5,20]]},"reference":[{"key":"1141_CR1","doi-asserted-by":"crossref","unstructured":"C. Agarwal, A. Sharma, Image understanding using decision tree based machine learning, in International Conference on Information Technology and Multimedia (IEEE, 2012), pp. 1\u20138","DOI":"10.1109\/ICIMU.2011.6122757"},{"key":"1141_CR2","doi-asserted-by":"crossref","unstructured":"E. Akafi, M. Vali, N. Moradi, Detection of hypernasal speech in children with cleft palate, in 19th Iranian Conference of Biomedical Engineering (ICBME) (IEEE, 2013), pp. 237\u2013241","DOI":"10.1109\/ICBME.2012.6519688"},{"key":"1141_CR3","unstructured":"A. Amelot, L. Crevier-Buchman, S. Maeda, Observations of velopharyngeal closure mechanism in horizontal and lateral direction from fiberscopic data, in 15th International Congress of Phonetic Sciences, 2003, pp. 3021\u20133024"},{"key":"1141_CR4","unstructured":"T. Ananthakrishna, K. Shama, U.C. Niranjan, k-means nearest neighbor classifier for voice pathology, in Proceedings of the IEEE Indicon (IEEE, 2004), pp. 352\u2013354"},{"issue":"15","key":"1141_CR5","first-page":"24","volume":"56","author":"V Ananthanatarajan","year":"2012","unstructured":"V. Ananthanatarajan, S. Jothilakshmi, Segmentation of continuous speech into consonant and vowel units using formant frequencies. Int. J. Comput. Appl. 56(15), 24\u201327 (2012)","journal-title":"Int. J. Comput. Appl."},{"issue":"5","key":"1141_CR6","doi-asserted-by":"publisher","first-page":"2589","DOI":"10.1121\/1.3216913","volume":"126","author":"M Andreas","year":"2009","unstructured":"M. Andreas, H.N. Florian, B. Tobias, N.T. Elmar, S. Florian, N. Emeka, S. Maria, Automatic detection of articulation disorders in children with cleft lip and palate. J. Acoust. Soc. Am. 126(5), 2589\u20132602 (2009)","journal-title":"J. Acoust. Soc. Am."},{"key":"1141_CR7","doi-asserted-by":"crossref","unstructured":"J.R.O. Arroyave, J.F.V. Bonilla, Automatic detection of hypernasality in children, in International Work-Conference on the Interplay Between Natural and Artificial Computation (IWINAC) (Springer, 2011), pp. 167\u2013174","DOI":"10.1007\/978-3-642-21326-7_19"},{"issue":"1","key":"1141_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2200000006","volume":"2","author":"Y Bengio","year":"2009","unstructured":"Y. Bengio, Learning deep architectures for AI. Found. Trends Mach. Learn. 2(1), 1\u2013127 (2009)","journal-title":"Found. Trends Mach. Learn."},{"issue":"8","key":"1141_CR9","doi-asserted-by":"publisher","first-page":"1553","DOI":"10.1109\/TNNLS.2013.2293637","volume":"25","author":"M Bianchini","year":"2014","unstructured":"M. Bianchini, F. Scarselli, On the complexity of neural network classifiers: a comparison between shallow and deep architectures. IEEE Trans. Neural Netw. Learn. Syst. 25(8), 1553\u20131565 (2014)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"1141_CR10","first-page":"9","volume":"43","author":"P Birch","year":"2002","unstructured":"P. Birch, B. Gumoes, S. Prytz, A. Karle, H. Stavad, J. Sundberg, Effects of a velopharyngeal opening on the sound transfer characteristics of the vowel [a]. Speech Music Hear. Q. Prog. Status Rep. 43, 9\u201315 (2002)","journal-title":"Speech Music Hear. Q. Prog. Status Rep."},{"key":"1141_CR11","doi-asserted-by":"crossref","unstructured":"T. Bocklet, K. Riedhammer, U. Eysholdt, E. N\u00f6th, Automatic phoneme analysis in children with Cleft Lip and Palate, in IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE, 2013), pp. 7572\u20137576","DOI":"10.1109\/ICASSP.2013.6639135"},{"issue":"1","key":"1141_CR12","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1109\/10.477699","volume":"43","author":"DA Cairns","year":"1996","unstructured":"D.A. Cairns, J.H. Hansen, J.E. Riski, A noninvasive technique for detecting hypernasal speech using a nonlinear operator. IEEE Trans. Biomed. Eng. 43(1), 35\u201345 (1996)","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"1141_CR13","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2763132","author":"MA Carbonneau","year":"2016","unstructured":"M.A. Carbonneau, E. Granger, Y. Attabi, G. Gagnon, Feature learning from spectrograms for assessment of personality traits. IEEE Trans. Affect. Comput. (2016). https:\/\/doi.org\/10.1109\/TAFFC.2017.2763132","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"11","key":"1141_CR14","doi-asserted-by":"publisher","first-page":"2355","DOI":"10.1109\/TMI.2017.2751523","volume":"36","author":"G Carneiro","year":"2017","unstructured":"G. Carneiro, J. Nascimento, A.P. Bradley, Automated analysis of unregistered multi-view mammograms with deep learning. IEEE Trans. Med. Imaging 36(11), 2355\u20132365 (2017)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"1141_CR15","doi-asserted-by":"crossref","unstructured":"G. Castellanos, G. Daza, L. Sanchez, O. Castrillon, J. Suarez, Acoustic speech analysis for hypernasality detection in children, in International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE, 2006), pp. 5507\u20135510","DOI":"10.1109\/IEMBS.2006.260572"},{"key":"1141_CR16","doi-asserted-by":"crossref","unstructured":"M. Cernak, S. Tong, Nasal speech sounds detection using connectionist temporal classification, in International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2018), pp. 5574\u20135578","DOI":"10.1109\/ICASSP.2018.8462149"},{"issue":"4","key":"1141_CR17","first-page":"758","volume":"26","author":"S Chambon","year":"2018","unstructured":"S. Chambon, M.N. Galtier, P.J. Arnal, G. Wainrib, A. Gramfort, A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series. IEEE Trans. Rehabil. Eng. 26(4), 758\u2013769 (2018)","journal-title":"IEEE Trans. Rehabil. Eng."},{"issue":"10","key":"1141_CR18","doi-asserted-by":"publisher","first-page":"6232","DOI":"10.1109\/TGRS.2016.2584107","volume":"54","author":"Y Chen","year":"2016","unstructured":"Y. Chen, H. Jiang, C. Li, X. Jia, P. Ghamisi, Deep feature extraction and classification of hyperspectral images based on convolutional neural networks. IEEE Trans. Geosci. Remote Sens. 54(10), 6232\u20136251 (2016)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"1141_CR19","unstructured":"C.D.L. Cruz, B. Santhanam, A joint EMD and Teager-Kaiser energy approach towards normal and nasal speech analysis, in 50th Asilomar Conference on Signals, Systems and Computers (IEEE, 2016), pp. 429\u2013433"},{"key":"1141_CR20","volume-title":"Discrete-Time Processing of Speech Signals","author":"JR Deller","year":"1993","unstructured":"J.R. Deller, J.H. Hansen, J.G. Proakis, Discrete-Time Processing of Speech Signals (Prentice-Hall, Englewood Cliffs, 1993)"},{"issue":"1","key":"1141_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1111\/crj.12367","volume":"10","author":"T Dodderi","year":"2016","unstructured":"T. Dodderi, M. Narra, S.M. Varghese, D.T. Deepak, Spectral analysis of hypernasality in cleft palate children: a pre-post surgery comparison. J. Clin. Diagn. Res. 10(1), 1\u20133 (2016)","journal-title":"J. Clin. Diagn. Res."},{"key":"1141_CR22","doi-asserted-by":"crossref","unstructured":"A.K. Dubey, S.M. Prasanna, S. Dandapat, Pitch-adaptive front-end feature for hypernasality detection, in Interspeech 2018, 2018, pp. 372\u2013376","DOI":"10.21437\/Interspeech.2018-1251"},{"key":"1141_CR23","doi-asserted-by":"crossref","unstructured":"A.K. Dubey, S.R.M. Prasanna, S. Dandapat, Zero time windowing analysis of hypernasality in speech of Cleft Lip and palate children, in Twenty Second National Conference on Communication (NCC) (IEEE, 2016), pp. 1\u20136","DOI":"10.1109\/NCC.2016.7561188"},{"issue":"5","key":"1141_CR24","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1121\/1.5039718","volume":"143","author":"AK Dubey","year":"2018","unstructured":"A.K. Dubey, A. Tripathi, S. Prasanna, S. Dandapat, Detection of hypernasality based on vowel space area. J. Acoust. Soc. Am. 143(5), 412\u2013417 (2018)","journal-title":"J. Acoust. Soc. Am."},{"issue":"1","key":"1141_CR25","first-page":"1","volume":"31","author":"T Fawcett","year":"2004","unstructured":"T. Fawcett, ROC graphs: notes and practical considerations for researchers. Mach. Learn. 31(1), 1\u201338 (2004)","journal-title":"Mach. Learn."},{"key":"1141_CR26","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.neunet.2017.02.013","volume":"92","author":"HM Fayek","year":"2017","unstructured":"H.M. Fayek, M. Lech, L. Cavedon, Evaluating deep learning architectures for speech emotion recognition. Neural Netw. 92, 60\u201368 (2017)","journal-title":"Neural Netw."},{"issue":"1","key":"1141_CR27","doi-asserted-by":"publisher","first-page":"1511","DOI":"10.1121\/1.427148","volume":"106","author":"WT Fitch","year":"1999","unstructured":"W.T. Fitch, J. Giedd, Morphology and development of the human vocal tract: a study using magnetic resonance imaging. J. Acoust. Soc. Am. 106(1), 1511\u20131522 (1999)","journal-title":"J. Acoust. Soc. Am."},{"issue":"5","key":"1141_CR28","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1109\/MEMB.2009.934248","volume":"28","author":"ES Fonseca","year":"2009","unstructured":"E.S. Fonseca, J.C. Pereira, Normal versus pathological voice signals. IEEE Eng. Med. Biol. Mag. 28(5), 44\u201348 (2009)","journal-title":"IEEE Eng. Med. Biol. Mag."},{"issue":"3","key":"1141_CR29","first-page":"16","volume":"10","author":"SK Gaikwad","year":"2010","unstructured":"S.K. Gaikwad, B.W. Gawali, P. Yannawar, A review on speech recognition technique. Int. J. Comput. Appl. 10(3), 16\u201324 (2010)","journal-title":"Int. J. Comput. Appl."},{"issue":"1","key":"1141_CR30","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1109\/TAU.1968.1161953","volume":"16","author":"LJ Gerstman","year":"1968","unstructured":"L.J. Gerstman, Classification of self-normalized vowels. IEEE Trans. Audio Electroacoust. 16(1), 78\u201380 (1968)","journal-title":"IEEE Trans. Audio Electroacoust."},{"issue":"3","key":"1141_CR31","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1016\/S0892-1997(97)80003-3","volume":"11","author":"HR Gilbert","year":"1997","unstructured":"H.R. Gilbert, M.P. Robb, Y. Chen, Formant frequency development: 15 to 36\u00a0months. J. Voice 11(3), 260\u2013266 (1997)","journal-title":"J. Voice"},{"key":"1141_CR32","unstructured":"X. Glorot, A. Bordes, Y. Bengio, Deep sparse rectifier neural networks, in Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, 2011, pp. 315\u2013323"},{"issue":"2","key":"1141_CR33","doi-asserted-by":"publisher","first-page":"929","DOI":"10.1121\/1.4976056","volume":"141","author":"M Golabbakhsh","year":"2017","unstructured":"M. Golabbakhsh, F. Abnavi, E.M. Kadkhodaei, F. Derakhshandeh, F. Khanlar, P. Rong, D.P. Kuehn, Automatic identification of hypernasality in normal and cleft lip and palate patients with acoustic analysis of speech. J. Acoust. Soc. Am. 141(2), 929\u2013935 (2017)","journal-title":"J. Acoust. Soc. Am."},{"key":"1141_CR34","doi-asserted-by":"crossref","unstructured":"S. Haque, M.H. Ali, A.K.M.F. Haque, Cross-gender acoustic differences in hypernasal speech and detection of hypernasality, in International Workshop on Computational Intelligence (IWCI) (IEEE, 2017), pp. 187\u2013191","DOI":"10.1109\/IWCI.2016.7860363"},{"issue":"9","key":"1141_CR35","first-page":"195","volume":"7","author":"S Haque","year":"2016","unstructured":"S. Haque, M. Hanif, A.K.M. Fazlul, Variability of acoustic features of hypernasality and it\u2019s assessment. Int. J. Adv. Comput. Sci. Appl. 7(9), 195\u2013201 (2016)","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"1141_CR36","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1016\/j.bspc.2017.07.027","volume":"39","author":"L He","year":"2018","unstructured":"L. He, J. Zhang, Q. Liu, J. Zhang, H. Yin, M. Lech, Automatic detection of glottal stop in cleft palate speech. Biomed. Signal Process. Control 39, 230\u2013236 (2018)","journal-title":"Biomed. Signal Process. Control"},{"issue":"10","key":"1141_CR37","doi-asserted-by":"publisher","first-page":"1298","DOI":"10.1109\/LSP.2014.2333061","volume":"21","author":"L He","year":"2014","unstructured":"L. He, J. Zhang, Q. Liu, H. Yin, M. Lech, Automatic evaluation of hypernasality and consonant misarticulation in cleft palate speech. IEEE Signal Process. Lett. 21(10), 1298\u20131301 (2014)","journal-title":"IEEE Signal Process. Lett."},{"issue":"1","key":"1141_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1597\/06-086.1","volume":"45","author":"G Henningsson","year":"2008","unstructured":"G. Henningsson, D.P. Kuehn, D. Sell, T. Sweeney, J.E. Trost-Cardamone, T.L. Whitehill, Universal parameters for reporting speech outcomes in individuals with cleft palate. Cleft Palate Craniofac. J. 45(1), 1\u201317 (2008)","journal-title":"Cleft Palate Craniofac. J."},{"issue":"1","key":"1141_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1597\/06-086.1","volume":"23","author":"GE Henningsson","year":"1986","unstructured":"G.E. Henningsson, A.M. Isberg, Velopharyngeal movement patterns in patients alternating between oral and glottal articulation: a clinical and cineradiographical study. Cleft Palate J. 23(1), 1\u20139 (1986)","journal-title":"Cleft Palate J."},{"issue":"1","key":"1141_CR40","doi-asserted-by":"publisher","first-page":"3099","DOI":"10.1121\/1.411872","volume":"97","author":"J Hillenbrand","year":"1995","unstructured":"J. Hillenbrand, L.A. Getty, M.J. Clark, K. Wheeler, Acoustic characteristics of American English vowels. J. Acoust. Soc. Am. 97(1), 3099\u20133111 (1995)","journal-title":"J. Acoust. Soc. Am."},{"key":"1141_CR41","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1007\/978-3-642-35289-8_32","volume-title":"Neural Networks: Tricks of the Trade","author":"GE Hinton","year":"2012","unstructured":"G.E. Hinton, A practical guide to training restricted Boltzmann machines, in Neural Networks: Tricks of the Trade, ed. by G. Montavon, G.B. Orr, K.R. M\u00fcller (Springer, Berlin, 2012), pp. 599\u2013619"},{"key":"1141_CR42","unstructured":"C. Huang, Analysis of speaker variability, in Seventh European Conference on Speech Communication and Technology (Eurospeech) (2001), pp. 1377\u20131380"},{"key":"1141_CR43","unstructured":"S. Ioffe, C. Szegedy, Batch normalization: Accelerating deep network training by reducing internal covariate shift, 2015. arXiv:1502.03167"},{"key":"1141_CR44","unstructured":"I. Jacobi, On variation and change in diphthongs and long vowels of spoken Dutch. Ph.D. Dissertation, Universiteit of Amsterdam, 2009"},{"issue":"1","key":"1141_CR45","doi-asserted-by":"publisher","first-page":"2181","DOI":"10.1121\/1.1360717","volume":"109","author":"R Kataoka","year":"2001","unstructured":"R. Kataoka, D.W. Warren, D.J. Zajac, R. Mayo, R.W. Lutz, The relationship between spectral characteristics and perceived hypernasality in children. J. Acoust. Soc. Am. 109(1), 2181\u20132189 (2001)","journal-title":"J. Acoust. Soc. Am."},{"key":"1141_CR46","unstructured":"D.P. Kingma, J. Ba, Adam: a method for stochastic optimization, 2014. arXiv preprint arXiv:1412.6980"},{"issue":"8","key":"1141_CR47","doi-asserted-by":"publisher","first-page":"1847","DOI":"10.1109\/TPAMI.2012.272","volume":"35","author":"N Kr\u00fcger","year":"2013","unstructured":"N. Kr\u00fcger, P. Janssen, S. Kalkan, M. Lappe, A. Leonardis, J. Piater, A.J. Rodr\u00edguezs\u00e1nchez, L. Wiskott, Deep hierarchies in the primate visual cortex: what can we learn for computer vision? IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1847\u20131871 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"7553","key":"1141_CR48","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"Y. LeCun, Y. Bengio, G. Hinton, Deep learning. Nature 521(7553), 436\u2013443 (2015)","journal-title":"Nature"},{"issue":"7","key":"1141_CR49","doi-asserted-by":"publisher","first-page":"1437","DOI":"10.1109\/TBME.2006.873694","volume":"53","author":"GS Lee","year":"2006","unstructured":"G.S. Lee, C.P. Wang, C.C. Yang, T.B. Kuo, Voice low tone to high tone ratio: a potential quantitative index for vowel [a:] and its nasalization. IEEE Trans. Biomed. Eng. 53(7), 1437\u20131439 (2006)","journal-title":"IEEE Trans. Biomed. Eng."},{"issue":"1","key":"1141_CR50","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1597\/07-184.1","volume":"46","author":"GS Lee","year":"2009","unstructured":"G.S. Lee, C.P. Wang, S. Fu, Evaluation of hypernasality in vowels using voice low tone to high tone ratio. Cleft Palate Craniofac. J. 46(1), 47\u201352 (2009)","journal-title":"Cleft Palate Craniofac. J."},{"issue":"3","key":"1141_CR51","doi-asserted-by":"publisher","first-page":"1455","DOI":"10.1121\/1.426686","volume":"105","author":"S Lee","year":"1999","unstructured":"S. Lee, A. Potamianos, S. Narayanan, Acoustics of children\u2019s speech: developmental changes of temporal and spectral parameters. J. Acoust. Soc. Am. 105(3), 1455\u20131468 (1999)","journal-title":"J. Acoust. Soc. Am."},{"key":"1141_CR52","doi-asserted-by":"crossref","unstructured":"C.X. Ling, J. Huang, H. Zhang, AUC: a better measure than accuracy in comparing learning algorithms, in Conference of the Canadian Society for Computational Studies of Intelligence (Springer, 2003), pp. 329\u2013341","DOI":"10.1007\/3-540-44886-1_25"},{"key":"1141_CR53","doi-asserted-by":"crossref","unstructured":"A. Maier, C. Hacker, E. Noth, E. Nkenke, T. Haderlein, F. Rosanowski, M. Schuster, Intelligibility of Children with cleft lip and palate: evaluation by speech recognition techniques, in 18th International Conference on Pattern Recognition (ICPR) (IEEE, 2006), pp. 274\u2013277","DOI":"10.1109\/ICPR.2006.718"},{"key":"1141_CR54","doi-asserted-by":"crossref","unstructured":"A. Maier, C. Hacker, M. Schuster, Analysis of hypernasal speech in children with cleft lip and palate, in International Conference on Text, Speech and Dialogue (TSD) (Springer, 2008), pp. 389\u2013396","DOI":"10.1007\/978-3-540-87391-4_50"},{"key":"1141_CR55","doi-asserted-by":"crossref","unstructured":"A. Mirzaei, M. Vali, Detection of hypernasality from speech signal using group delay and wavelet transform, in 6th International Conference on Computer and Knowledge Engineering (ICCKE) (IEEE, 2017), pp. 189\u2013193","DOI":"10.1109\/ICCKE.2016.7802138"},{"issue":"5","key":"1141_CR56","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1597\/1545-1569_1994_031_0356_movcfd_2.3.co_2","volume":"31","author":"JB Moon","year":"1994","unstructured":"J.B. Moon, D.P. Kuehn, J.J. Huisman, Measurement of velopharyngeal closure force during vowel production. Cleft Palate Craniofac. J. 31(5), 356\u2013363 (1994)","journal-title":"Cleft Palate Craniofac. J."},{"issue":"2","key":"1141_CR57","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/j.specom.2006.11.004","volume":"49","author":"D Morrison","year":"2007","unstructured":"D. Morrison, R. Wang, L.C. De Silva, Ensemble methods for spoken emotion recognition in call-centres. Speech Commun. 49(2), 98\u2013112 (2007)","journal-title":"Speech Commun."},{"key":"1141_CR58","doi-asserted-by":"crossref","unstructured":"R.G. Nieto, J.I. Mar\u00edn-Hurtado, L.M. Capacho-Valbuena, A.A. Suarez, Pattern recognition of hypernasality in voice of patients with cleft and lip palate, in XIX Symposium on Image, Signal Processing and Artificial Vision (IEEE, 2015), pp. 1\u20135","DOI":"10.1109\/STSIVA.2014.7010187"},{"key":"1141_CR59","doi-asserted-by":"crossref","unstructured":"K. Nikitha, S. Kalita, C. Vikram, M. Pushpavathi, S.M. Prasanna, Hypernasality severity analysis in cleft lip and palate speech using vowel space area, in Interspeech, 2017, pp. 1829\u20131833","DOI":"10.21437\/Interspeech.2017-1245"},{"issue":"4","key":"1141_CR60","first-page":"15","volume":"26","author":"L Nord","year":"1985","unstructured":"L. Nord, G. Ericsson, Acoustic investigation of cleft palate speech before and after speech therapy. Speech Transm. Lab. Q. Prog. Status Rep. 26(4), 15\u201327 (1985)","journal-title":"Speech Transm. Lab. Q. Prog. Status Rep."},{"issue":"4","key":"1141_CR61","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1007\/s12559-012-9166-z","volume":"5","author":"JR Orozco-Arroyave","year":"2013","unstructured":"J.R. Orozco-Arroyave, J.F. Vargas-Bonilla, J.D. Arias-Londo\u00f1o, S. Murillo-Rend\u00f3n, G. Castellanos-Dom\u00ednguez, J.F. Garc\u00e9s, Nonlinear dynamics for hypernasality detection in spanish vowels and words. Cognit. Comput. 5(4), 448\u2013457 (2013)","journal-title":"Cognit. Comput."},{"issue":"6","key":"1141_CR62","doi-asserted-by":"publisher","first-page":"1820","DOI":"10.1109\/JBHI.2015.2467375","volume":"19","author":"JR Orozco-Arroyave","year":"2015","unstructured":"J.R. Orozco-Arroyave, J.D. Arias-Londo\u00f1o, J.F. Vargas-Bonilla, S. Skodda, J. Rusz, K. Daqrouq, F. H\u00f6nig, E. N\u00f6th, Characterization methods for the detection of multiple voice disorders: neurological, functional, and laryngeal diseases. IEEE J. Biomed. Health Inform. 19(6), 1820\u20131828 (2015)","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"1141_CR63","doi-asserted-by":"crossref","unstructured":"D. Palaz, R. Collobert, Analysis of cnn-based speech recognition system using raw speech as input, in Interspeech, 2015, pp. 11\u201315","DOI":"10.21437\/Interspeech.2015-3"},{"issue":"3","key":"1141_CR64","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1121\/1.393949","volume":"80","author":"A Parush","year":"1986","unstructured":"A. Parush, D.J. Ostry, Superior lateral pharyngeal wall movements in speech. J. Acoust. Soc. Am. 80(3), 749\u2013756 (1986)","journal-title":"J. Acoust. Soc. Am."},{"issue":"5\u20136","key":"1141_CR65","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1159\/000259999","volume":"37","author":"DB Pisoni","year":"1980","unstructured":"D.B. Pisoni, Variability of vowel formant frequencies and the quantal theory of speech: a first report. Phonetica 37(5\u20136), 285\u2013305 (1980)","journal-title":"Phonetica"},{"key":"1141_CR66","doi-asserted-by":"crossref","unstructured":"R. Prasad, S.R. Kadiri, S.V. Gangashetty, B. Yegnanarayana, Discriminating nasals and approximants in English language using zero time windowing, in Interspeech 2018, 2018, pp. 177\u2013181","DOI":"10.21437\/Interspeech.2018-1032"},{"issue":"7","key":"1141_CR67","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1114\/1.1380422","volume":"29","author":"DK Rah","year":"2001","unstructured":"D.K. Rah, Y.L. Ko, C. Lee, D.W. Kim, A noninvasive estimation of hypernasality using a linear predictive model. Ann. Biomed. Eng. 29(7), 587\u2013594 (2001)","journal-title":"Ann. Biomed. Eng."},{"key":"1141_CR68","first-page":"156","volume":"13","author":"W Ryan","year":"1976","unstructured":"W. Ryan, C. Hawkins, Ultrasonic measurement of lateral pharyngeal wall movement at the velopharyngeal port. Cleft Palate J. 13, 156\u2013164 (1976)","journal-title":"Cleft Palate J."},{"key":"1141_CR69","doi-asserted-by":"crossref","unstructured":"L. Salhi, A. Cherif, Selection of pertinent acoustic features for detection of pathological voices, in 5th International Conference on Modeling, Simulation and Applied Optimization (ICMSAO) (IEEE, 2013), pp. 1\u20136","DOI":"10.1109\/ICMSAO.2013.6552723"},{"key":"1141_CR70","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","volume":"61","author":"J Schmidhuber","year":"2015","unstructured":"J. Schmidhuber, Deep learning in neural networks: an overview. Neural Netw. 61, 85\u2013117 (2015)","journal-title":"Neural Netw."},{"issue":"3","key":"1141_CR71","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1016\/j.ijporl.2011.12.010","volume":"76","author":"M Schuster","year":"2012","unstructured":"M. Schuster, A. Maier, T. Bocklet, E. Nkenke, A. Holst, U. Eysholdt, F. Stelzle, Automatically evaluated degree of intelligibility of children with different cleft type from preschool and elementary school measured by automatic speech recognition. Int. J. Pediatr. Otorhinolaryngol. 76(3), 362\u2013369 (2012)","journal-title":"Int. J. Pediatr. Otorhinolaryngol."},{"issue":"1","key":"1141_CR72","doi-asserted-by":"publisher","first-page":"2344","DOI":"10.1121\/1.415421","volume":"99","author":"BL Smith","year":"1996","unstructured":"B.L. Smith, M.K. Kenney, S. Hussain, A longitudinal investigation of duration and temporal variability in children\u2019s speech production. J. Acoust. Soc. Am. 99(1), 2344\u20132349 (1996)","journal-title":"J. Acoust. Soc. Am."},{"issue":"1","key":"1141_CR73","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, R. Salakhutdinov, Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"issue":"6","key":"1141_CR74","doi-asserted-by":"publisher","first-page":"3858","DOI":"10.1121\/1.2722220","volume":"121","author":"P Tarun","year":"2007","unstructured":"P. Tarun, C.Y. Espy-Wilson, B.H. Story, Simulation and analysis of nasalized vowels based on magnetic resonance imaging data. J. Acoust. Soc. Am. 121(6), 3858\u20133873 (2007)","journal-title":"J. Acoust. Soc. Am."},{"key":"1141_CR75","doi-asserted-by":"crossref","unstructured":"E. Verteletskaya, K. Sakhnov, B. Simak, Pitch detection algorithms and voiced\/unvoiced classification for noisy speech, in International Conference on Systems, Signals and Image Processing (IEEE, 2009), pp. 1\u20135","DOI":"10.1109\/IWSSIP.2009.5367778"},{"key":"1141_CR76","doi-asserted-by":"crossref","unstructured":"P. Vijayalakshmi, T. Nagarajan, J. Rav, Selective pole modification-based technique for the analysis and detection of hypernasality, in IEEE Region 10 Conference TENCON 2009\u20132009 (IEEE, 2009), pp. 1\u20135","DOI":"10.1109\/TENCON.2009.5396117"},{"issue":"4","key":"1141_CR77","doi-asserted-by":"publisher","first-page":"621","DOI":"10.1109\/TBME.2006.889191","volume":"54","author":"P Vijayalakshmi","year":"2007","unstructured":"P. Vijayalakshmi, M.R. Reddy, O.S. Douglas, Acoustic analysis and detection of hypernasality using a group delay function. IEEE Trans. Biomed. Eng. 54(4), 621\u2013629 (2007)","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"1141_CR78","doi-asserted-by":"crossref","unstructured":"C.M. Vikram, A. Tripathi, S. Kalita, S.R. Mahadeva Prasanna, Estimation of hypernasality scores from cleft lip and palate speech, in Interspeech, 2018, pp. 1701\u20131705","DOI":"10.21437\/Interspeech.2018-1631"},{"issue":"6","key":"1141_CR79","doi-asserted-by":"publisher","first-page":"1640","DOI":"10.1044\/1092-4388(2009\/08-0161)","volume":"52","author":"AP Vogel","year":"2009","unstructured":"A.P. Vogel, H.M. Ibrahim, S. Reilly, N. Kilpatrick, A comparative study of two acoustic measures of hypernasality. J. Speech Lang. Hear. Res. 52(6), 1640\u20131651 (2009)","journal-title":"J. Speech Lang. Hear. Res."},{"issue":"8","key":"1141_CR80","first-page":"123","volume":"54","author":"XY Wang","year":"2018","unstructured":"X.Y. Wang, Y.P. Huang, J.H. Qian, L. He, H. Huang, H. Yin, Initial and final segmentation in cleft palate speech based on acoustic characteristics. Comput. Eng. Appl. 54(8), 123\u2013136 (2018)","journal-title":"Comput. Eng. Appl."},{"key":"1141_CR81","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1162\/tacl_a_00097","volume":"4","author":"W Yin","year":"2015","unstructured":"W. Yin, H. Sch\u00fctze, B. Xiang, B. Zhou, Abcnn: attention-based convolutional neural network for modeling sentence pairs. Trans. Assoc. Comput. Linguist. 4, 259\u2013272 (2015)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"1141_CR82","unstructured":"W. Zhang, G. Li, L. Wang, Application of improved spectral subtraction algorithm for speech emotion recognition, in Fifth International Conference on Big Data and Cloud Computing (IEEE, 2015), pp. 213\u2013216"}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-019-01141-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00034-019-01141-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-019-01141-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,18]],"date-time":"2022-09-18T10:14:05Z","timestamp":1663496045000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00034-019-01141-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,20]]},"references-count":82,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2019,8]]}},"alternative-id":["1141"],"URL":"https:\/\/doi.org\/10.1007\/s00034-019-01141-x","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"type":"print","value":"0278-081X"},{"type":"electronic","value":"1531-5878"}],"subject":[],"published":{"date-parts":[[2019,5,20]]},"assertion":[{"value":"31 August 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 May 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 May 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 May 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}