{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:26:30Z","timestamp":1740122790571,"version":"3.37.3"},"reference-count":68,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,9,14]],"date-time":"2022-09-14T00:00:00Z","timestamp":1663113600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,9,14]],"date-time":"2022-09-14T00:00:00Z","timestamp":1663113600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100008895","name":"Tertiary Education Trust Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008895","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1007\/s10772-022-09984-7","type":"journal-article","created":{"date-parts":[[2022,9,14]],"date-time":"2022-09-14T15:02:56Z","timestamp":1663167776000},"page":"307-336","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Mining speech signal patterns for robust speaker variability classification"],"prefix":"10.1007","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6774-5259","authenticated-orcid":false,"given":"Moses Effiong","family":"Ekpenyong","sequence":"first","affiliation":[]},{"given":"Odudu-Obong Uwem","family":"Udocox","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,9,14]]},"reference":[{"issue":"2","key":"9984_CR1","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1515\/jall.2003.006","volume":"24","author":"A Akinlabi","year":"2003","unstructured":"Akinlabi, A., & Urua, E. E. (2003). Foot structure in the Ibibio verb. Journal of African Languages and Linguistics, 24(2), 119\u2013160.","journal-title":"Journal of African Languages and Linguistics"},{"key":"9984_CR2","doi-asserted-by":"crossref","unstructured":"Aronowitz, H., & Barkan, O. (2012). Efficient approximated i-vector extraction. In Proceedings of IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 4789\u20134792).","DOI":"10.1109\/ICASSP.2012.6288990"},{"issue":"3","key":"9984_CR3","doi-asserted-by":"publisher","first-page":"1001","DOI":"10.1007\/s00180-020-00987-z","volume":"35","author":"C Beaulac","year":"2020","unstructured":"Beaulac, C., & Rosenthal, J. S. (2020). BEST: A decision tree algorithm that handles missing values. Computational Statistics, 35(3), 1001\u20131026.","journal-title":"Computational Statistics"},{"issue":"1","key":"9984_CR4","first-page":"97","volume":"32","author":"T Bent","year":"2006","unstructured":"Bent, T., Bradlow, A. R., & Wright, B. A. (2006). The influence of linguistic experience on the cognitive processing of pitch in speech and nonspeech sounds. Journal of Experimental Psychology: Human Perception and Performance, 32(1), 97.","journal-title":"Journal of Experimental Psychology: Human Perception and Performance"},{"issue":"4","key":"9984_CR5","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0060676","volume":"8","author":"GM Bidelman","year":"2013","unstructured":"Bidelman, G. M., Hutka, S., & Moreno, S. (2013). Tone language speakers and musicians share enhanced perceptual and cognitive abilities for musical pitch: Evidence for bidirectionality between the domains of language and music. PLoS ONE, 8(4), e60676.","journal-title":"PLoS ONE"},{"issue":"06","key":"9984_CR6","doi-asserted-by":"publisher","first-page":"1459","DOI":"10.1017\/S0142716414000496","volume":"36","author":"D Burnham","year":"2015","unstructured":"Burnham, D., Kasisopa, B., Reid, A., Luksaneeyanawin, S., Lacerda, F., Attina, V., Rattanasone, N. X., Schwarz, I. C., & Webster, D. (2015). Universality and language-specific experience in the perception of lexical tone and pitch. Applied Psycholinguistics, 36(06), 1459\u20131491.","journal-title":"Applied Psycholinguistics"},{"key":"9984_CR7","volume-title":"Recording and storing of speech data","author":"N Campbell","year":"2002","unstructured":"Campbell, N. (2002). Recording and storing of speech data. JST\/CREST Expressive Speech Processing Project."},{"issue":"01","key":"9984_CR8","doi-asserted-by":"publisher","first-page":"20","DOI":"10.38094\/jastt20165","volume":"2","author":"B Charbuty","year":"2021","unstructured":"Charbuty, B., & Abdulazeez, A. (2021). Classification based on decision tree algorithm for machine learning. Journal of Applied Science and Technology Trends, 2(01), 20\u201328.","journal-title":"Journal of Applied Science and Technology Trends"},{"issue":"6","key":"9984_CR9","doi-asserted-by":"publisher","first-page":"751","DOI":"10.1080\/23273798.2016.1156715","volume":"31","author":"A Chen","year":"2016","unstructured":"Chen, A., Liu, L., & Kager, R. (2016). Cross-domain correlation in pitch perception, the influence of native language. Language, Cognition and Neuroscience, 31(6), 751\u2013760.","journal-title":"Language, Cognition and Neuroscience"},{"key":"9984_CR10","doi-asserted-by":"crossref","unstructured":"Cooper, A., & Wang, Y. (2010). Cantonese tone word learning by tone and non-tone language speakers. In Proceedings of INTERSPEECH conference (pp. 1840\u20131843).","DOI":"10.21437\/Interspeech.2010-533"},{"issue":"3","key":"9984_CR11","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/BF00994018","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273\u2013297.","journal-title":"Machine Learning"},{"issue":"4","key":"9984_CR12","doi-asserted-by":"publisher","first-page":"1071","DOI":"10.1007\/s11831-019-09344-w","volume":"27","author":"S Dargan","year":"2020","unstructured":"Dargan, S., Kumar, M., Ayyagari, M. R., & Kumar, G. (2020). A survey of deep learning and its applications: A new paradigm to machine learning. Archives of Computational Methods in Engineering, 27(4), 1071\u20131092.","journal-title":"Archives of Computational Methods in Engineering"},{"key":"9984_CR13","unstructured":"Dehak, N., Dehak, R., Glass, J. R., Reynolds, D. A., & Kenny, P. (2010a). Cosine similarity scoring without score normalization techniques. In Proceedings of Odyssey 2010 \u2013 The speaker and language recognition workshop (pp. 71\u201375)."},{"issue":"4","key":"9984_CR14","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2010","unstructured":"Dehak, N., Kenny, P. J., Dehak, R., Dumouchel, P., & Ouellet, P. (2010b). Front-end factor analysis for speaker verification. IEEE Transactions on Audio, Speech, and Language Processing, 19(4), 788\u2013798.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9984_CR15","doi-asserted-by":"crossref","unstructured":"Dehak, N., Torres-Carrasquillo, P. A., Reynolds, D., & Dehak, R. (2011). Language recognition via i-vectors and dimensionality reduction. In Proceedings of INTERSPEECH conference (pp. 1\u20134).","DOI":"10.21437\/Interspeech.2011-328"},{"key":"9984_CR16","unstructured":"Diaz de Maria, F., & Figueiras-Vidal, A. R. (1995). Radial basis functions for nonlinear prediction of speech in analysis-by-synthesis coders. In Proceedings of IEEE workshop on non-linear signal and image processing (pp. 788\u2013791)."},{"key":"9984_CR17","doi-asserted-by":"crossref","unstructured":"Dighe, P., Luyet, G., Asaei, A., & Bourlard, H. (2016, March). Exploiting low-dimensional structures to enhance DNN based acoustic modeling in speech recognition. In 2016 IEEE International conference on acoustics, speech and signal processing (ICASSP) (pp. 5690\u20135694).","DOI":"10.1109\/ICASSP.2016.7472767"},{"key":"9984_CR21","doi-asserted-by":"crossref","unstructured":"Ekpenyong, M. E. (2018c). Adaptive template-based front end for tone language speech synthesis. In Human Language Technologies for Under-Resourced African Languages (pp. 1\u201329). Cham: Springer.","DOI":"10.1007\/978-3-319-69960-8_1"},{"key":"9984_CR18","doi-asserted-by":"crossref","unstructured":"Ekpenyong, M. E., Inyang, U. G., Edoho, M. E., & Urua, E-A. (2018a). Intra-speaker variability assessment for speaker recognition in degraded conditions: A case study of African tone languages. In Ekpenyong M. E. (Ed.). Human Language Technologies for Under-Resourced African Languages: Design, Challenges, and Prospects, SpringerBriefs in Electrical and Computer Engineering (pp.\u00a031\u201384).\u00a0Switzerland: Cham.","DOI":"10.1007\/978-3-319-69960-8_2"},{"key":"9984_CR20","doi-asserted-by":"crossref","unstructured":"Ekpenyong, M., Inyang, U. & Udoh, E. O. (2018b). Unsupervised visualization of under-resourced speech prosody. Speech Communication, 101(2018), 45\u201356.","DOI":"10.1016\/j.specom.2018.04.011"},{"key":"9984_CR19","doi-asserted-by":"crossref","unstructured":"Ekpenyong, M., Urua, E. A., Watts, O., King, S. & Yamagishi, J. (2014). Statistical parametric speech synthesis for Ibibio. Speech Communication, 56, 243\u2013251.","DOI":"10.1016\/j.specom.2013.02.003"},{"issue":"1","key":"9984_CR22","first-page":"1","volume":"30","author":"M Faundez-Zanuy","year":"2002","unstructured":"Faundez-Zanuy, M., McLaughlin, S., Esposito, A., Hussain, A., Schoentgen, J., Kubin, G., Kleijn, W. B., & Maragos, P. (2002). Nonlinear speech processing: Overview and applications. Control and Intelligent Systems., 30(1), 1\u201310.","journal-title":"Control and Intelligent Systems."},{"issue":"1","key":"9984_CR23","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/BF00994007","volume":"8","author":"UM Fayyad","year":"1992","unstructured":"Fayyad, U. M., & Irani, K. B. (1992). On the handling of continuous-valued attributes in decision tree generation. Machine Learning, 8(1), 87\u2013102.","journal-title":"Machine Learning"},{"issue":"3","key":"9984_CR24","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1007\/s11222-010-9179-y","volume":"21","author":"N Friel","year":"2011","unstructured":"Friel, N., & Pettitt, A. N. (2011). Classification using distance nearest neighbours. Statistics and Computing, 21(3), 431\u2013437.","journal-title":"Statistics and Computing"},{"key":"9984_CR25","doi-asserted-by":"crossref","unstructured":"Garcia-Romero, D., & Espy-Wilson, C. Y. (2011). Analysis of i-vector length normalization in speaker recognition systems. In Proceedings of INTERSPEECH\u00a0(pp. 249\u2013252).","DOI":"10.21437\/Interspeech.2011-53"},{"key":"9984_CR26","unstructured":"Gibbon, D., Ahoua, F., Gb\u00e9ry, E., Urua, E., & Ekpenyong, M. (2004). WALA: A multilingual resource repository for West African languages. In M. T. Lino, M. F. Xavier, F. Ferreira, R. Costa, & S. Silva (Eds.), Proceedings of 4th International conference on language resources and evaluation conference (LREC), Vol. II, (pp. 579\u2013582)."},{"key":"9984_CR27","first-page":"509","volume-title":"The Oxford handbook of corpus phonology","author":"U Gut","year":"2014","unstructured":"Gut, U. (2014). The LeaP Corpus. In D. Jacques, U. Gut, & K. Gjert (Eds.), The Oxford handbook of corpus phonology (pp. 509\u2013516). Oxford University Press."},{"key":"9984_CR28","doi-asserted-by":"crossref","unstructured":"Hatch, A. O., Kajarekar, S., & Stolcke, A. (2006). Within-Class covariance normalization for SVM-based speaker recognition. In Proceedings of 9th International conference on speech language processing (pp. 1471\u20131474).","DOI":"10.21437\/Interspeech.2006-183"},{"key":"9984_CR29","unstructured":"Heselwood, B., & Plug, L. (2011). The role of F2 and F3 in the perception of rhoticity: Evidence from listening experiments. In Proceedings of ICPhS."},{"key":"9984_CR30","doi-asserted-by":"crossref","unstructured":"Huang, C., Chen, T., Li, S. Z., Chang, E., & Zhou, J. L. (2001). Analysis of speaker variability. In INTERSPEECH (pp. 1377\u20131380).","DOI":"10.21437\/Eurospeech.2001-356"},{"key":"9984_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2007\/76030","volume":"2007","author":"A Ikeno","year":"2007","unstructured":"Ikeno, A., & Hansen, J. H. (2007). The effect of listener accent background on accent perception and comprehension. EURASIP Journal on Audio, Speech, and Music Processing, 2007, 1\u20138.","journal-title":"EURASIP Journal on Audio, Speech, and Music Processing"},{"issue":"3","key":"9984_CR32","doi-asserted-by":"publisher","first-page":"2019","DOI":"10.1121\/1.3385266","volume":"127","author":"T Isei-Jaakkola","year":"2010","unstructured":"Isei-Jaakkola, T., Naka, T., & Hirose, K. (2010). Comparison of the formant frequencies F3 and F4 on a three-dimensional vowel chart. The Journal of the Acoustical Society of America, 127(3), 2019\u20132019.","journal-title":"The Journal of the Acoustical Society of America"},{"key":"9984_CR33","unstructured":"Jian, F. H-L. (1999). Taiwanese tone Sandhi viewed from an intensity perspective. In Proceedings of ICPhS99\u00a0(pp. 2387\u20132390). San Francisco."},{"issue":"2","key":"9984_CR34","doi-asserted-by":"publisher","first-page":"83","DOI":"10.3390\/e19020083","volume":"19","author":"T Kanamori","year":"2017","unstructured":"Kanamori, T., Fujiwara, S., & Takeda, A. (2017). Breakdown point of robust support vector machines. Entropy, 19(2), 83.","journal-title":"Entropy"},{"issue":"5","key":"9984_CR35","doi-asserted-by":"publisher","first-page":"980","DOI":"10.1109\/TASL.2008.925147","volume":"16","author":"P Kenny","year":"2008","unstructured":"Kenny, P., Ouellet, P., Dehak, N., Gupta, V., & Dumouchel, P. (2008). A study of interspeaker variability in speaker verification. IEEE Transactions on Audio, Speech, and Language Processing, 16(5), 980\u2013988.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9984_CR36","unstructured":"King, B. P. (2015). Practical natural language processing for low-resource languages. Doctoral Thesis, University of Michigan."},{"key":"9984_CR37","first-page":"1","volume":"10","author":"H Larochelle","year":"2009","unstructured":"Larochelle, H., Bengio, Y., Louradour, J., & Lamblin, P. (2009). Exploring strategies for training deep neural networks. Journal of Machine Learning Research, 10, 1\u201340.","journal-title":"Journal of Machine Learning Research"},{"key":"9984_CR38","doi-asserted-by":"crossref","unstructured":"Li, M., Zhang, X., Yan, Y., & Narayanan, S. (2011). Speaker verification using sparse representations on total variability I-vectors. In Proceedings of INTERSPEECH conference (pp. 1\u20134).","DOI":"10.21437\/Interspeech.2011-149"},{"key":"9984_CR39","unstructured":"Ma, B., Zhu, D., & Tong, R. (2006). Chinese dialect identification using tone features based on pitch flux. In Proceedings of international conference on acoustics, speech and signal processing."},{"key":"9984_CR40","doi-asserted-by":"crossref","unstructured":"McLaren, M., & van Leeuwen, D. (2011). Improved speaker recognition when using i-vectors from multiple speech sources. In Proceedings of IEEE International conference on acoustics, speech and signal processing (ICASSP) (pp. 5460\u20135463).","DOI":"10.1109\/ICASSP.2011.5947594"},{"key":"9984_CR41","first-page":"43","volume":"3","author":"A Michaud","year":"2015","unstructured":"Michaud, A., & Vaissiere, J. (2015). Tone and intonation: Introductory notes and practical recommendations. Theoretical and Empirical Foundations of Experimental Phonetics, 3, 43\u201380.","journal-title":"Theoretical and Empirical Foundations of Experimental Phonetics"},{"issue":"2","key":"9984_CR42","first-page":"63","volume":"22","author":"V Narang","year":"2012","unstructured":"Narang, V., Misra, D., & Yadav. (2012). F1 and F2 correlation with F0: A study of vowels of Hindi, Punjabi, Korean and Thai. International Journal of Asian Language Prrocessing, 22(2), 63\u201373.","journal-title":"International Journal of Asian Language Prrocessing"},{"key":"9984_CR43","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1109\/79.221324","volume":"10","author":"CL Nikias","year":"1993","unstructured":"Nikias, C. L., & Mendel, J. M. (1993). Signal processing with higher-order spectra. IEEE Signal Processing Magazine, 10, 10\u201337.","journal-title":"IEEE Signal Processing Magazine"},{"key":"9984_CR44","first-page":"23","volume-title":"83","author":"OA Odejobi","year":"2008","unstructured":"Odejobi, O. A. (2008). Recognition of tones in Yoruba speech: Experiments with artificial neural networks, In B. Prasad & S. R. M. Prasanna (Eds.),\u00a0Speech, audio, image and biomedical signal processing using neural networks. Studies Computational Intelligence (SCI), Volume 83,\u00a0(pp. 23\u201347). Springer."},{"key":"9984_CR45","doi-asserted-by":"crossref","unstructured":"Paillereau, N. M. (2016). Do isolated vowels represent vowel targets in French? An acoustic study on coarticulation. In SHS Web of Conferences (Vol. 27, p. 09003). EDP Sciences.","DOI":"10.1051\/shsconf\/20162709003"},{"key":"9984_CR46","volume-title":"Introduction to data mining","author":"T Pang-Ning","year":"2006","unstructured":"Pang-Ning, T., Steinbach, M., & Kumar, V. (2006). Introduction to data mining. Pearson Addison Wesley."},{"key":"9984_CR47","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1016\/j.wocn.2018.09.008","volume":"71","author":"AR Plummer","year":"2018","unstructured":"Plummer, A. R., & Reidy, P. F. (2018). Computing low-dimensional representations of speech from socio-auditory structures for phonetic analyses. Journal of Phonetics, 71, 355\u2013375.","journal-title":"Journal of Phonetics"},{"key":"9984_CR48","volume-title":"Introductory signal processing","author":"R Priemer","year":"1991","unstructured":"Priemer, R. (1991). Introductory signal processing. World Scientific Publishers."},{"key":"9984_CR49","doi-asserted-by":"crossref","unstructured":"Rajan, P., Kinnunen, T., & Hautam\u00e4ki, V. (2013). Effect of multicondition training on i-vector PLDA configurations for speaker recognition. In Proceedings of INTERSPEECH (pp. 3694\u20133697).","DOI":"10.21437\/Interspeech.2013-693"},{"key":"9984_CR50","unstructured":"Reynolds, D. A. (1992). A Gaussian mixture modeling approach to text-independent speaker identification, Ph.D. Thesis, Georgia Institute of Technology."},{"issue":"1\u20133","key":"9984_CR51","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1006\/dspr.1999.0361","volume":"10","author":"DA Reynolds","year":"2000","unstructured":"Reynolds, D. A., Quatieri, T. F., & Dunn, R. B. (2000). Speaker verification using adapted Gaussian mixture models. Digital Signal Processing, 10(1\u20133), 19\u201341.","journal-title":"Digital Signal Processing"},{"issue":"1","key":"9984_CR52","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1121\/1.5117167","volume":"146","author":"J Schertz","year":"2019","unstructured":"Schertz, J., Chow, C. T. Y., & Kamal, N. S. N. (2019). The influence of tone language experience and speech style on the use of intonation in language discrimination. The Journal of the Acoustical Society of America, 146(1), 58\u201364.","journal-title":"The Journal of the Acoustical Society of America"},{"key":"9984_CR53","doi-asserted-by":"crossref","unstructured":"Schwanh\u00e4u\u00dfer, B., & Burnham, D. (2005). Lexical tone and pitch perception in tone and non-tone language speakers. In Ninth European conference on speech communication and technology.","DOI":"10.21437\/Interspeech.2005-278"},{"issue":"1","key":"9984_CR54","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1196\/annals.1360.018","volume":"1060","author":"JA Sloboda","year":"2005","unstructured":"Sloboda, J. A., Wise, K. J., & Peretz, I. (2005). Quantifying tone deafness in the general population. Annals of the New York Academy of Sciences, 1060(1), 255\u2013261.","journal-title":"Annals of the New York Academy of Sciences"},{"issue":"1","key":"9984_CR55","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1177\/0305735611415749","volume":"41","author":"CJ Stevens","year":"2013","unstructured":"Stevens, C. J., Keller, P. E., & Tyler, M. D. (2013). Tonal language background and detecting pitch contour in spoken and musical items. Psychology of Music, 41(1), 59\u201374.","journal-title":"Psychology of Music"},{"key":"9984_CR56","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.chemolab.2017.02.004","volume":"163","author":"H Sun","year":"2017","unstructured":"Sun, H., & Hu, X. (2017). Attribute selection for decision tree learning with class constraint. Chemometrics and Intelligent Laboratory Systems, 163, 16\u201323.","journal-title":"Chemometrics and Intelligent Laboratory Systems"},{"key":"9984_CR57","first-page":"145","volume":"1","author":"PN Tan","year":"2006","unstructured":"Tan, P. N., Steinbach, M., & Kumar, V. (2006). Classification: Basic concepts, decision trees, and model evaluation. Introduction to Data Mining, 1, 145\u2013205.","journal-title":"Introduction to Data Mining"},{"key":"9984_CR58","doi-asserted-by":"crossref","unstructured":"Terasawa, H., Slaney, M. and Berger, J. (2005). A timbre space for speech. In Proceedings of INTERSPEECH.","DOI":"10.21437\/Interspeech.2005-285"},{"issue":"2","key":"9984_CR59","doi-asserted-by":"publisher","first-page":"169","DOI":"10.3233\/AIC-170729","volume":"30","author":"A Tharwat","year":"2017","unstructured":"Tharwat, A., Gaber, T., Ibrahim, A., & Hassanien, A. E. (2017). Linear discriminant analysis: A detailed tutorial. AI Communications, 30(2), 169\u2013190.","journal-title":"AI Communications"},{"key":"9984_CR60","unstructured":"Thyssen, J., Nielsen, H., & Hansen, S. D. (1994). Non-linear short term prediction in speech coding, In Proceedings of international conference on acoustics, speech and signal processing (pp. I-185\u2013I-188)."},{"key":"9984_CR61","unstructured":"Tian, Y., Zhou, J. L., Chu, M., & Chang, E. (2004). Tone recognition with fractionized models and outlined features. In Proceedings of IEEE International conference on acoustics, speech, and signal processing (ICASSP\u201904) (pp. 1\u20134)."},{"key":"9984_CR62","doi-asserted-by":"crossref","unstructured":"Townshend, B. (1991). Non-linear prediction of speech. In Proceedings of international conference on acoustic speech signal (pp. 425\u2013428).","DOI":"10.1109\/ICASSP.1991.150367"},{"key":"9984_CR63","doi-asserted-by":"crossref","unstructured":"Tu, Y. H., Tashev, I., Zarar, S., & Lee, C. H. (2018). A hybrid approach to combining conventional and deep learning techniques for single-channel speech enhancement and recognition. In 2018 IEEE International conference on acoustics, speech and signal processing (ICASSP) (pp. 2531\u20132535).","DOI":"10.1109\/ICASSP.2018.8461944"},{"key":"9984_CR64","unstructured":"Uddin, A. N., Rahman, M. A., Islam, M., & Haque, M. A. (2018). Native language identification using i-vector. arXiv:1811.05540."},{"key":"9984_CR65","unstructured":"Urua, E. (2000). Ibibio phonetics and phonology. Centre for Advanced Studies of African Societies."},{"key":"9984_CR66","doi-asserted-by":"crossref","unstructured":"Yu, A. C. L. (2010). Tonal effects on perceived vowel duration. Laboratory Phonology, 10(4), 151\u2013168.","DOI":"10.1515\/9783110224917.2.151"},{"issue":"1","key":"9984_CR67","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1109\/MSP.2010.939038","volume":"28","author":"D Yu","year":"2011","unstructured":"Yu, D., & Deng, L. (2011). Deep learning and its applications to signal and information processing. IEEE Signal Process. Magazine, 28(1), 145\u2013154.","journal-title":"IEEE Signal Process. Magazine"},{"key":"9984_CR68","doi-asserted-by":"crossref","unstructured":"Yu, H., & Yang, J. (2001). A direct LDA algorithm for high-dimensional data\u2014with application to face recognition. Pattern recognition, 34(10), 2067\u20132070.","DOI":"10.1016\/S0031-3203(00)00162-X"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-022-09984-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-022-09984-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-022-09984-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,31]],"date-time":"2023-07-31T11:13:28Z","timestamp":1690802008000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-022-09984-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,14]]},"references-count":68,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,7]]}},"alternative-id":["9984"],"URL":"https:\/\/doi.org\/10.1007\/s10772-022-09984-7","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2022,9,14]]},"assertion":[{"value":"26 August 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 September 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}