{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:27:01Z","timestamp":1740122821163,"version":"3.37.3"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2018,8,28]],"date-time":"2018-08-28T00:00:00Z","timestamp":1535414400000},"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"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1007\/s10772-018-9543-4","type":"journal-article","created":{"date-parts":[[2018,8,28]],"date-time":"2018-08-28T11:54:54Z","timestamp":1535457294000},"page":"915-930","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Three-stage speaker verification architecture in emotional talking environments"],"prefix":"10.1007","volume":"21","author":[{"given":"Ismail","family":"Shahin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali Bou","family":"Nassif","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,8,28]]},"reference":[{"key":"9543_CR1","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1016\/S0167-6393(02)00083-3","volume":"40","author":"LT Bosch","year":"2003","unstructured":"Bosch, L. T. (2003). Emotions, speech and the ASR framework. Speech Communication, 40, 213\u2013225.","journal-title":"Speech Communication"},{"key":"9543_CR2","doi-asserted-by":"crossref","unstructured":"Chen, L., Lee, K. A., Chng, E.-S., Ma, B., Li, H., & Dai, L. R., (2016). Content-aware local variability vector for speaker verification with short utterance. In The 41st IEEE international conference on acoustics, speech and signal processing, Shanghai, China, March 2016 (pp.\u00a05485\u20135489).","DOI":"10.1109\/ICASSP.2016.7472726"},{"key":"9543_CR3","unstructured":"Emotional Prosody Speech and Transcripts dataset. (2016). Retrieved November 15, 2016, from http:\/\/www.ldc.upenn.edu\/Catalog\/CatalogEntry. jsp?catalogId = LDC2002S28 ."},{"issue":"6","key":"9543_CR4","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1109\/MSP.2015.2462851","volume":"32","author":"JHL Hansen","year":"2015","unstructured":"Hansen, J. H. L., & Hasan, T., (2015). Speaker recognition by machines and humans: a tutorial review. IEEE Signal Processing Magazine, 32(6), 74\u201399.","journal-title":"IEEE Signal Processing Magazine"},{"key":"9543_CR5","doi-asserted-by":"crossref","unstructured":"Harb, H., & Chen, L. (2003). Gender identification using a general audio classifier. In International Conference on Multimedia and Expo 2003 (ICME\u201903), July 2003, (pp. 733\u2013736).","DOI":"10.1109\/ICME.2003.1221721"},{"issue":"4","key":"9543_CR6","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1109\/TAFFC.2015.2495222","volume":"7","author":"MX Huang","year":"2016","unstructured":"Huang, M. X., Ngai, G., Hua, K. A., Chan, S. C. F., & Leong, H. V. (2016). Identifying user-specific facial affects from spontaneous expressions with minimal annotation. IEEE Transactions on Affective Computing, 7(4), 360\u2013373. https:\/\/doi.org\/10.1109\/TAFFC.2015.2495222 .","journal-title":"IEEE Transactions on Affective Computing"},{"issue":"2","key":"9543_CR7","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1109\/TSA.2004.838534","volume":"13","author":"CM Lee","year":"2005","unstructured":"Lee, C. M., & Narayanan, S. S. (2005). Towards detecting emotions in spoken dialogs. IEEE Transactions on Speech and Audio Processing, 13(2), 293\u2013303.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"4","key":"9543_CR8","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1109\/TAFFC.2015.2490070","volume":"7","author":"S Mariooryad","year":"2016","unstructured":"Mariooryad, S., & Busso, C. (2016). Facial expression recognition in the presence of speech using blind lexical compensation. IEEE Transactions on Affective Computing, 7(4), 346\u2013359. https:\/\/doi.org\/10.1109\/TAFFC.2015.2490070 .","journal-title":"IEEE Transactions on Affective Computing"},{"issue":"10","key":"9543_CR9","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1016\/j.specom.2008.04.010","volume":"50","author":"L Mary","year":"2008","unstructured":"Mary, L., & Yegnanarayana, B. (2008). Extraction and representation of prosodic features for language and speaker recognition. Speech Communication, 50(10), 782\u2013796.","journal-title":"Speech Communication"},{"key":"9543_CR10","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1016\/S0167-6393(03)00099-2","volume":"41","author":"TL Nwe","year":"2003","unstructured":"Nwe, T. L., Foo, S. W., & De Silva, L. C. (2003). Speech emotion recognition using hidden Markov models. Speech Communication, 41, 603\u2013623.","journal-title":"Speech Communication"},{"issue":"4","key":"9543_CR11","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1049\/iet-spr.2008.0175","volume":"3","author":"SG Pillay","year":"2009","unstructured":"Pillay, S. G., Ariyaeeinia, A., Pawlewski, M., & Sivakumaran, P. (2009). Speaker verification under mismatched data conditions. IET Signal Processing, 3(4), 236\u2013246.","journal-title":"IET Signal Processing"},{"issue":"12","key":"9543_CR12","doi-asserted-by":"publisher","first-page":"1206","DOI":"10.1016\/j.specom.2009.06.005","volume":"51","author":"V Pitsikalis","year":"2009","unstructured":"Pitsikalis, V., & Maragos, P. (2009). Analysis and classification of speech signals by generalized fractal dimension features. Speech Communication, 51(12), 1206\u20131223.","journal-title":"Speech Communication"},{"key":"9543_CR13","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1007\/s10772-010-9068-y","volume":"13","author":"J Pittermann","year":"2010","unstructured":"Pittermann, J., Pittermann, A., & Minker, W. (2010). Emotion recognition and adaptation in spoken dialogue systems. International Journal of Speech Technology, 13, 49\u201360.","journal-title":"International Journal of Speech Technology"},{"key":"9543_CR14","unstructured":"Polzin, T. S., & Waibel, A. H., (1998). Detecting emotions in speech. Cooperative multimodal communication. In second international conference 1998, CMC 1998."},{"issue":"2","key":"9543_CR15","first-page":"173","volume":"8","author":"DA Reynolds","year":"1995","unstructured":"Reynolds, D. A. (1995). Automatic speaker recognition using Gaussian mixture speaker models. The Lincoln Laboratory Journal, 8(2), 173\u2013192.","journal-title":"The Lincoln Laboratory Journal"},{"key":"9543_CR16","first-page":"IV-4072","volume":"4","author":"DA Reynolds","year":"2002","unstructured":"Reynolds, D. A. (2002). An overview of automatic speaker recognition technology. ICASSP 2002, 4, IV-4072\u2013IV-4075.","journal-title":"ICASSP 2002"},{"issue":"1\u20133","key":"9543_CR17","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"},{"key":"9543_CR18","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1109\/ICOSP.2000.891634","volume":"2","author":"KR Scherer","year":"2000","unstructured":"Scherer, K. R., Johnstone, T., Klasmeyer, G., & Banziger, T. (2000). Can automatic speaker verification be improved by training the algorithms on emotional speech? Proceedings of International Conference on Spoken Language Processing, 2, 807\u2013810.","journal-title":"Proceedings of International Conference on Spoken Language Processing"},{"issue":"11","key":"9543_CR19","doi-asserted-by":"publisher","first-page":"2700","DOI":"10.1016\/j.sigpro.2008.05.012","volume":"88","author":"I Shahin","year":"2008","unstructured":"Shahin, I. (2008). Speaker identification in the shouted environment using suprasegmental hidden Markov models. Signal Processing, 88(11), 2700\u20132708.","journal-title":"Signal Processing"},{"key":"9543_CR28","doi-asserted-by":"crossref","unstructured":"Shahin, I. (2009). Verifying speakers in emotional environments. In The 9th IEEE international symposium on signal processing and information technology, Ajman, United Arab Emirates, December 2009, (pp.\u00a0328\u2013333).","DOI":"10.1109\/ISSPIT.2009.5407568"},{"issue":"2","key":"9543_CR20","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. International Journal of Speech Technology, 14(2), 89\u201398. https:\/\/doi.org\/10.1007\/s10772-011-9089-1 .","journal-title":"International Journal of Speech Technology"},{"key":"9543_CR21","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, CHMM2s and SPHMMs. Journal on Multimodal User Interfaces, 6, 59\u201371. https:\/\/doi.org\/10.1007\/s12193-011-0082-4 .","journal-title":"Journal on Multimodal User Interfaces"},{"issue":"3","key":"9543_CR22","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1007\/s10772-013-9188-2","volume":"16","author":"I Shahin","year":"2013","unstructured":"Shahin, I. (2013a). Employing both gender and emotion cues to enhance speaker identification performance in emotional talking environments. International Journal of Speech Technology, 16(3), 341\u2013351. https:\/\/doi.org\/10.1007\/s10772-013-9188-2 .","journal-title":"International Journal of Speech Technology"},{"key":"9543_CR23","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. (2013b). Speaker identification in emotional talking environments based on CSPHMM2s. Engineering Applications of Artificial Intelligence, 26, 1652\u20131659. https:\/\/doi.org\/10.1016\/j.engappai.2013.03.013 .","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"2","key":"9543_CR24","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/s10772-012-9170-4","volume":"16","author":"I Shahin","year":"2013","unstructured":"Shahin, I. (2013c). Gender-dependent emotion recognition based on HMMs and SPHMMs. International Journal of Speech Technology, 16(2), 133\u2013141. https:\/\/doi.org\/10.1007\/s10772-012-9170-4 .","journal-title":"International Journal of Speech Technology"},{"key":"9543_CR25","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. Engineering Applications of Artificial Intelligence, 35, 316\u2013323. https:\/\/doi.org\/10.1016\/j.engappai.2014.07.006 .","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"1","key":"9543_CR26","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1515\/jisys-2014-0118","volume":"25","author":"I Shahin","year":"2016","unstructured":"Shahin, I. (2016). Employing emotion cues to verify speakers in emotional talking environments. Journal of Intelligent Systems, Special Issue on Intelligent Healthcare Systems, 25(1), 3\u201317. https:\/\/doi.org\/10.1515\/jisys-2014-0118 .","journal-title":"Journal of Intelligent Systems, Special Issue on Intelligent Healthcare Systems"},{"issue":"1","key":"9543_CR27","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/s10772-014-9251-7","volume":"18","author":"I Shahin","year":"2015","unstructured":"Shahin, I., & Ba-Hutair, M. N. (2015). Talking condition recognition in stressful and emotional talking environments based on CSPHMM2s. International Journal of Speech Technology, 18(1), 77\u201390, https:\/\/doi.org\/10.1007\/s10772-014-9251-7 .","journal-title":"International Journal of Speech Technology"},{"issue":"9","key":"9543_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 Communication, 48(9), 1162\u20131181.","journal-title":"Speech Communication"},{"key":"9543_CR30","unstructured":"Vogt, T., & Andre, E., (2006). Improving automatic emotion recognition from speech via gender differentiation. In Proceedings of Language Resources and Evaluation Conference (LREC 2006), Genoa, Italy, 2006."},{"key":"9543_CR31","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.specom.2016.02.004","volume":"79","author":"L Wang","year":"2016","unstructured":"Wang, L., Wang, J., Li, L., Zheng, T. F., & Soong, F. K. (2016). Improving speaker verification performance against long-term speaker variability. Speech Communication, 79, 14\u201329.","journal-title":"Speech Communication"},{"key":"9543_CR32","doi-asserted-by":"crossref","unstructured":"Wu, W., Zheng, T. F., Xu, M. X., & Bao, H. J., (2006). Study on speaker verification on emotional speech. In Proceedings of International Conference on Spoken Language Processing, INTERSPEECH 2006. September 2006, (pp.\u00a02102\u20132105).","DOI":"10.21437\/Interspeech.2006-191"},{"issue":"4","key":"9543_CR33","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1109\/TSA.2005.848892","volume":"13","author":"B Yegnanarayana","year":"2005","unstructured":"Yegnanarayana, B., Prasanna, S. R. M., Zachariah, J. M., & Gupta, C. S. (2005). Combining evidence from source, suprasegmental and spectral features for a fixed-text speaker verification systems. IEEE Transactions on Speech and Audio Processing, 13(4), 575\u2013582.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"3","key":"9543_CR34","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1109\/89.905995","volume":"9","author":"G Zhou","year":"2001","unstructured":"Zhou, G., Hansen, J. H. L., & Kaiser, J. F. (2001). Nonlinear feature based classification of speech under stress. IEEE Transactions on Speech & Audio Processing, 9(3), 201\u2013216.","journal-title":"IEEE Transactions on Speech & Audio Processing"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-018-9543-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-018-9543-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-018-9543-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,30]],"date-time":"2022-08-30T17:34:37Z","timestamp":1661880877000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-018-9543-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8,28]]},"references-count":34,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2018,12]]}},"alternative-id":["9543"],"URL":"https:\/\/doi.org\/10.1007\/s10772-018-9543-4","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2018,8,28]]},"assertion":[{"value":"3 April 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This study does not involve any animal participants.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}