{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T21:54:51Z","timestamp":1775253291541,"version":"3.50.1"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2018,10,4]],"date-time":"2018-10-04T00:00:00Z","timestamp":1538611200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100002724","name":"University of sharjah","doi-asserted-by":"crossref","award":["1602040348-P"],"award-info":[{"award-number":["1602040348-P"]}],"id":[{"id":"10.13039\/501100002724","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100002724","name":"University of sharjah","doi-asserted-by":"crossref","award":["1602040349-P"],"award-info":[{"award-number":["1602040349-P"]}],"id":[{"id":"10.13039\/501100002724","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2020,4]]},"DOI":"10.1007\/s00521-018-3760-2","type":"journal-article","created":{"date-parts":[[2018,10,4]],"date-time":"2018-10-04T16:21:54Z","timestamp":1538670114000},"page":"2575-2587","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":49,"title":["Novel cascaded Gaussian mixture model-deep neural network classifier for speaker identification in emotional talking environments"],"prefix":"10.1007","volume":"32","author":[{"given":"Ismail","family":"Shahin","sequence":"first","affiliation":[]},{"given":"Ali Bou","family":"Nassif","sequence":"additional","affiliation":[]},{"given":"Shibani","family":"Hamsa","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,4]]},"reference":[{"key":"3760_CR1","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1016\/0167-6393(91)90054-W","volume":"10","author":"S Furui","year":"1991","unstructured":"Furui S (1991) Speaker-dependent-feature-extraction, recognition and processing techniques. Speech Commun 10:505\u2013520","journal-title":"Speech Commun"},{"key":"3760_CR2","first-page":"1975","volume":"7","author":"Y Wang","year":"2012","unstructured":"Wang Y, Tang F, Zheng U (2012) Robust text-independent speaker identification in a time-varying noisy environment. J Softw 7:1975\u20131980","journal-title":"J Softw"},{"issue":"1","key":"3760_CR3","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1109\/79.911197","volume":"18","author":"R Cowie","year":"2001","unstructured":"Cowie R, Douglas-Cowie E, Tsapatsoulis N, Votsis G, Collias S, Fellenz W, Taylor J (2001) Emotion recognition in human-computer interaction. IEEE Signal Process Mag 18(1):32\u201380","journal-title":"IEEE Signal Process Mag"},{"key":"3760_CR4","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1016\/j.neunet.2005.03.006","volume":"18","author":"N Fragopanagos","year":"2005","unstructured":"Fragopanagos N, Taylor JG (2005) Emotion recognition in human-computer interaction. Neural Netw 18:389\u2013405 (Special issue)","journal-title":"Neural Netw"},{"issue":"7","key":"3760_CR5","doi-asserted-by":"publisher","first-page":"1652","DOI":"10.1016\/j.engappai.2013.03.013","volume":"26","author":"I Shahin","year":"2013","unstructured":"Shahin I (2013) Speaker identification in emotional talking environments based on CSPHMM2\u00a0s. Eng Appl Artif Intell 26(7):1652\u20131659. https:\/\/doi.org\/10.1016\/j.engappai.2013.03.013","journal-title":"Eng Appl Artif Intell"},{"key":"3760_CR6","doi-asserted-by":"crossref","unstructured":"Li D, Yang Y, Wu Z, Wu T (2005) Emotion-state conversion for speaker recognition. In: Affective computing and intelligent interaction. LNCS, vol 3784. Springer, Berlin, pp 403\u2013410","DOI":"10.1007\/11573548_52"},{"key":"3760_CR7","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1016\/j.specom.2010.08.013","volume":"53","author":"S Wu","year":"2011","unstructured":"Wu S, Falk TH, Chan WY (2011) Automatic speech emotion recognition using modulation spectral features. Speech Commun 53:768\u2013785","journal-title":"Speech Commun"},{"key":"3760_CR8","doi-asserted-by":"crossref","unstructured":"Bao H, Xu M, Zheng TF (2007) Emotion attribute projection for speaker recognition on emotional speech. In: Proceedings of the 8th MLPual conference of the international speech communication association (Interspeech\u201907), Antwerp, Belgium, pp 601\u2013604","DOI":"10.21437\/Interspeech.2007-142"},{"key":"3760_CR9","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/s10772-010-9085-x","volume":"14","author":"SG Koolagudi","year":"2011","unstructured":"Koolagudi SG, Krothapalli RS (2011) Two stage emotion recognition based on speaking rate. Int J Speech Technol 14:35\u201348","journal-title":"Int J Speech Technol"},{"key":"3760_CR10","doi-asserted-by":"crossref","unstructured":"Jawarkar NP, Holambe RS, Basu TK (2012) Text-independent speaker identification in emotional environments: a classifier fusion approach. In: Frontiers in computer education, Volume 133 of the series advances in intelligent and soft computing, pp 569\u2013576","DOI":"10.1007\/978-3-642-27552-4_77"},{"key":"3760_CR11","doi-asserted-by":"crossref","unstructured":"Mansour A, Lachiri Z (2016) Emotional speaker recognition in simulated and spontaneous context. In: 2nd International conference on advanced technologies for signal and image processing (ATSIP), pp 776\u2013781","DOI":"10.1109\/ATSIP.2016.7523187"},{"issue":"2","key":"3760_CR12","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/s10772-011-9089-1","volume":"14","author":"I Shahin","year":"2011","unstructured":"Shahin I (2011) Identifying speakers using their emotion cues. Int J Speech Technol 14(2):89\u201398. https:\/\/doi.org\/10.1007\/s10772-011-9089-1","journal-title":"Int J Speech Technol"},{"issue":"3","key":"3760_CR13","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1007\/s10772-013-9188-2","volume":"16","author":"I Shahin","year":"2013","unstructured":"Shahin I (2013) Employing both gender and emotion cues to enhance speaker identification performance in emotional talking environments. Int J Speech Technol 16(3):341\u2013351. https:\/\/doi.org\/10.1007\/s10772-013-9188-2","journal-title":"Int J Speech Technol"},{"key":"3760_CR14","doi-asserted-by":"crossref","unstructured":"Shahin I, Nasser Ba-Hutair M (2014) Emarati speaker identification. In: 12th International conference on signal processing (ICSP 2014), HangZhou, China, pp 488\u2013493","DOI":"10.1109\/ICOSP.2014.7015053"},{"issue":"1","key":"3760_CR15","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/s12193-011-0082-4","volume":"6","author":"I Shahin","year":"2012","unstructured":"Shahin I (2012) Studying and enhancing talking condition recognition in stressful and emotional talking environments based on HMMs, CHMM2\u00a0s and SPHMMs. J Multimodal User Interfaces 6(1):59\u201371. https:\/\/doi.org\/10.1007\/s12193-011-0082-4","journal-title":"J Multimodal User Interfaces"},{"issue":"1","key":"3760_CR16","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/s10772-014-9251-7","volume":"18","author":"I Shahin","year":"2015","unstructured":"Shahin I, Nasser Ba-Hutair M (2015) Talking condition recognition in stressful and emotional talking environments based on CSPHMM2s. Int J Speech Technol 18(1):77\u201390. https:\/\/doi.org\/10.1007\/s10772-014-9251-7","journal-title":"Int J Speech Technol"},{"key":"3760_CR17","unstructured":"George T, Fabien R, Raymond B, Erik M, Mihalis AN, Bj\u00f6rn S, Stefanos Z (2016) Adieu features? End-to-end speech emotion recognition using a deep convolutional recurrent network. In: IEEE international conference on acoustics, speech and signal processing (ICASSP)"},{"key":"3760_CR18","unstructured":"Erik MS, Youngmoo EK (2011) Learning emotion-based acoustic features with deep belief networks. In: 2011 IEEE workshop on applications of signal processing to audio and acoustics, pp 16\u201319"},{"key":"3760_CR19","doi-asserted-by":"crossref","unstructured":"Matejka P, Glembek O, Navotny O, Plchot O, Grezl F, Burget L, Cernocky J (2016) Analysis of DNN approaches to speaker identification. In: International conference on acoustics, speech and signal processing, pp 5100\u20135104","DOI":"10.1109\/ICASSP.2016.7472649"},{"key":"3760_CR20","first-page":"1096","volume-title":"Advances in neural information processing systems","author":"H Lee","year":"2009","unstructured":"Lee H, Pham P, Largman Y, Ng A (2009) Unsupervised feature learning for audio classification using convolutional deep belief networks. In: Bengio Y, Schuurmans D, Lafferty J, Williams CKI, Culotta A (eds) Advances in neural information processing systems, vol 22. MIT Press, Cambridge, pp 1096\u20131104"},{"issue":"10","key":"3760_CR21","doi-asserted-by":"publisher","first-page":"1671","DOI":"10.1109\/LSP.2015.2420092","volume":"22","author":"F Richardson","year":"2015","unstructured":"Richardson F, Reynolds D, Dehak N (2015) Deep neural network approaches to speaker and language recognition. IEEE Signal Process Lett 22(10):1671\u20131675","journal-title":"IEEE Signal Process Lett"},{"issue":"6","key":"3760_CR22","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1007\/s00521-016-2501-7","volume":"29","author":"H Ali","year":"2018","unstructured":"Ali H, Tran SN, Benetos E, d\u2019Avila Garcez AS (2018) Speaker recognition with hybrid features from a deep belief network. Neural Comput Appl 29(6):13\u201319. https:\/\/doi.org\/10.1007\/s00521-016-2501-7","journal-title":"Neural Comput Appl"},{"issue":"2","key":"3760_CR23","first-page":"7","volume":"87","author":"N Geeta","year":"2014","unstructured":"Geeta N, Soni MK (2014) Speaker recognition using support vector machine. Int J Comput Appl 87(2):7\u201310","journal-title":"Int J Comput Appl"},{"key":"3760_CR24","unstructured":"Marcel K, Sven EK, Martin S, Edin A, Andreas W (2016) Speaker identification and verification using support vector machines and sparse kernel logistic regression. In: International workshop on intelligent computing in pattern analysis\/synthesis (IWICPAS), pp 176\u2013184"},{"key":"3760_CR25","unstructured":"Sharma A, Snghand SP, Kumar VK (2005) Text-independent speaker identification using back propagation MLP network classifier for a closed set of speakers. In: Proceedings of the fifth IEEE international symposium on signal processing and information technology"},{"key":"3760_CR26","first-page":"109","volume":"7","author":"V Srinivas","year":"2014","unstructured":"Srinivas V, Santhi Rani C, Madhu T (2014) Neural network based classification for speaker identification. Int J Signal Process Image Process Pattern Recognit 7:109\u2013120","journal-title":"Int J Signal Process Image Process Pattern Recognit"},{"key":"3760_CR27","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/s10462-012-9368-5","volume":"43","author":"CN Anagnostopoulos","year":"2012","unstructured":"Anagnostopoulos CN, Iliou T, Giannoukos I (2012) Features and classifiers for emotion recognition from speech: a survey from 2000 to 2011. Artif Intell Rev 43:155\u2013177. https:\/\/doi.org\/10.1007\/s10462-012-9368-5","journal-title":"Artif Intell Rev"},{"key":"3760_CR28","unstructured":"Adell J, Benafonte A, Escudero D (2005) Analysis of prosodic features: towards modeling of emotional and pragmatic attributes of speech. XXI Congreso de la Sociedad Espa\u00f1ola para el Procesamiento del Lenguaje Natural, SEPLN, Granada, Spain"},{"issue":"9","key":"3760_CR29","doi-asserted-by":"publisher","first-page":"1162","DOI":"10.1016\/j.specom.2006.04.003","volume":"48","author":"D Ververidis","year":"2006","unstructured":"Ververidis D, Kotropoulos C (2006) Emotional speech recognition: resources, features and methods. Speech Commun 48(9):1162\u20131181","journal-title":"Speech Commun"},{"issue":"1\u20132","key":"3760_CR30","first-page":"213","volume":"40","author":"LT Bosch","year":"2003","unstructured":"Bosch LT (2003) Emotions, speech and the ASR framework. Speech Commun 40(1\u20132):213\u2013225","journal-title":"Speech Commun"},{"key":"3760_CR31","unstructured":"http:\/\/practicalcryptography.com\/miscellaneous\/machine-learning\/guide-mel-frequency-cepstral-coefficients-mfccs\/"},{"key":"3760_CR32","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1109\/89.365379","volume":"3","author":"DA Reynold","year":"1995","unstructured":"Reynold DA (1995) Robust text independent speaker identification using Gaussian mixture speaker models. IEEE Trans Speech Audio Process 3:72\u201382","journal-title":"IEEE Trans Speech Audio Process"},{"key":"3760_CR33","doi-asserted-by":"crossref","unstructured":"McLaren M, Lei Y, Scheffer N, Ferrer L (2014) Application of convolutional neural networks to speaker recognition in noisy conditions. In: Interspeech, pp 686\u2013690","DOI":"10.21437\/Interspeech.2014-172"},{"key":"3760_CR34","unstructured":"Xu B, Wang N, Chen T, Li M (2015) Empirical evaluation of rectified activations in convolution network, pp 1\u20135. arXiv:1505.00853v2"},{"key":"3760_CR35","volume-title":"Chapter 4: Introduction to mathematical statistics","author":"RV Hogg","year":"1970","unstructured":"Hogg RV, Craig AT (1970) Chapter 4: Introduction to mathematical statistics. Collier-Macmillan, London"},{"key":"3760_CR36","doi-asserted-by":"crossref","unstructured":"Hansen JHL, Bou-Ghazale S (1997) Getting started with SUSAS: a speech under simulated and actual stress database. In: International conference on speech communication and technology, EUROSPEECH-97, Rhodes, Greece, vol 4, pp 1743\u20131746","DOI":"10.21437\/Eurospeech.1997-494"},{"key":"3760_CR37","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1016\/j.engappai.2014.07.006","volume":"35","author":"I Shahin","year":"2014","unstructured":"Shahin I (2014) Novel third-order hidden Markov models for speaker identification in shouted talking environments. Eng Appl Artif Intell 35:316\u2013323. https:\/\/doi.org\/10.1016\/j.engappai.2014.07.006","journal-title":"Eng Appl Artif Intell"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-018-3760-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00521-018-3760-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-018-3760-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,3]],"date-time":"2022-09-03T08:47:37Z","timestamp":1662194857000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00521-018-3760-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,4]]},"references-count":37,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2020,4]]}},"alternative-id":["3760"],"URL":"https:\/\/doi.org\/10.1007\/s00521-018-3760-2","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,10,4]]},"assertion":[{"value":"21 August 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 September 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 October 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This study does not involve any experiments on animals.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Human and animal rights"}},{"value":"This study includes very few speakers who are less than 18\u00a0years old. A consent from the minors\u2019 parents was provided before conducting the experiments.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent of parents\u2019 of minors"}}]}}