{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T03:38:34Z","timestamp":1762659514565,"version":"3.37.3"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2016,10,1]],"date-time":"2016-10-01T00:00:00Z","timestamp":1475280000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"crossref","award":["61231002"],"award-info":[{"award-number":["61231002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Doctoral Fund of Ministry of Education of China","award":["20110092130004"],"award-info":[{"award-number":["20110092130004"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1007\/s10772-016-9371-3","type":"journal-article","created":{"date-parts":[[2016,10,1]],"date-time":"2016-10-01T14:54:41Z","timestamp":1475333681000},"page":"805-816","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Emotional speech feature normalization and recognition based on speaker-sensitive feature clustering"],"prefix":"10.1007","volume":"19","author":[{"given":"Chengwei","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baolin","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,10,1]]},"reference":[{"key":"9371_CR1","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1007\/BF02339490","volume":"1","author":"JC Bezdek","year":"1974","unstructured":"Bezdek, J. C. (1974). Clustering validity with fuzzy sets. Journal of Mathematical Biology, 1, 57\u201371.","journal-title":"Journal of Mathematical Biology"},{"key":"9371_CR2","doi-asserted-by":"crossref","unstructured":"Burkhardt, F., Paeschke, A., Rolfes, M., Sendlmeier, W., & Weiss, B. (2005). A database of German emotional speech. Proceedings of the interspeech, Lissabon, Portugal (pp. 1517\u20131520).","DOI":"10.21437\/Interspeech.2005-446"},{"issue":"1","key":"9371_CR3","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1016\/j.csda.2006.04.030","volume":"51","author":"C Dring","year":"2006","unstructured":"Dring, C., Lesot, M. J., & Kruse, R. (2006). Data analysis with fuzzy clustering method. Computational Statistics and Data Analysi, 51(1), 192\u2013214.","journal-title":"Computational Statistics and Data Analysi"},{"key":"9371_CR4","unstructured":"Eyben, F., Woellmer, M., & Schuller, B. (2010). Opensmile, the munich versatile and fast open-source audio feature extractor. In Proceedings of the ACM international conference on multimedia (pp. 1459\u20131462)."},{"key":"9371_CR5","doi-asserted-by":"crossref","unstructured":"Hansen, J., & Bou-Ghazale, S. (1997). Getting started with SUSAS: A speech under simulated and actual stress database. In Proceedings of Eurospeech, Rhodes, Greece.","DOI":"10.21437\/Eurospeech.1997-494"},{"key":"9371_CR6","doi-asserted-by":"crossref","first-page":"112","DOI":"10.3724\/SP.J.1146.2009.00886","volume":"33","author":"C Huang","year":"2011","unstructured":"Huang, C., Zhao, Y., Jin, Y., Yu, Y., & Zhao, L. (2011). A study on feature analysis and recognition for practical speech emotion. Journal of Electronics & Information Technology, 33, 112\u2013116.","journal-title":"Journal of Electronics & Information Technology"},{"issue":"9-10","key":"9371_CR7","doi-asserted-by":"crossref","first-page":"1172","DOI":"10.1016\/j.specom.2011.01.007","volume":"53","author":"M Kockmann","year":"2011","unstructured":"Kockmann, M., Burget, L., & Cernocky, J. H. (2011). Application of speaker- and language identiffication state-of-the-art techniques for emotion recognition. Speech Communication, 53(9-10), 1172\u20131185.","journal-title":"Speech Communication"},{"key":"9371_CR8","doi-asserted-by":"crossref","unstructured":"K\u00fcstner, D., Tato, R., Kemp, T., & Meffert, B. (2004). Towards real life applications in emotion recognition, In Proceedings of the workshop on affective dialogue systems, Kloster Irsee (pp. 25\u201335).","DOI":"10.1007\/978-3-540-24842-2_3"},{"key":"9371_CR9","unstructured":"Li, J. (2015). Novel fuzzy clustering algorithm based on nature inspired computation, PhD thesis, Xidian University."},{"key":"9371_CR10","doi-asserted-by":"crossref","unstructured":"Li, Y., Chao, L., Liu, Y. et al. (2015). From simulated speech to natural speech, what are the robust features for emotion recognition? In Proceedings of the IEEE international conference on affective computing and intelligent interaction (ACII) (pp. 368\u2013373).","DOI":"10.1109\/ACII.2015.7344597"},{"key":"9371_CR11","unstructured":"Martin, O., Kotsia, I., Macq, B., & Pitas, I. (2006). The eNTERFACE\u201905 audio-visual emotion database. In Proceedings of the international conference on data engineering workshops."},{"issue":"4","key":"9371_CR12","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1007\/s005210070006","volume":"9","author":"J Nicholson","year":"2000","unstructured":"Nicholson, J., Takahashi, K., & Nakatsu, R. (2000). Emotion recognition in speech using neural networks. Neural Computing & Applications, 9(4), 290\u2013296.","journal-title":"Neural Computing & Applications"},{"key":"9371_CR13","unstructured":"Nwe, T. L., Foo, S. W., & De Silva, L. C. (2001). Speech based emotion classification. In Proceedings of the IEEE region 10 international conference on electrical and electronic technology, Phuket Island, Langkawi Island, Singapore (pp. 297\u2013301)."},{"issue":"4","key":"9371_CR14","doi-asserted-by":"crossref","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., & Silva, L. C. D. (2003). Speech emotion recognition using hidden Markov models. Speech Communication, 41(4), 603\u2013623.","journal-title":"Speech Communication"},{"issue":"1","key":"9371_CR15","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1007\/s10772-016-9333-9","volume":"19","author":"HK Palo","year":"2016","unstructured":"Palo, H. K., Mohanty, M. N., & Chandra, M. (2016). Efficient feature combination techniques for emotional speech classification. International Journal of Speech Technology, 19(1), 135\u2013150.","journal-title":"International Journal of Speech Technology"},{"key":"9371_CR16","unstructured":"pcDuino: Mini PC + Arduino (TM) [ http:\/\/www.pcduino.com\/ ]."},{"key":"9371_CR17","doi-asserted-by":"crossref","unstructured":"Rachuri, K. K., Musolesi, M., Mascolo, C., Rentfrow, P. J., Longworth, C., & Aucinas, A. (2010). EmotionSense: A mobile phones based adaptive platform for experimental social psychology, In Proceedings of the 12th ACM international conference on ubiquitous computing, Copenhagen (pp. 281\u2013290).","DOI":"10.1145\/1864349.1864393"},{"key":"9371_CR18","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/S0019-9958(69)90591-9","volume":"15","author":"EH Ruspini","year":"1969","unstructured":"Ruspini, E. H. (1969). A new approach to clustering. Information and Control, 15, 22\u201332.","journal-title":"Information and Control"},{"key":"9371_CR19","unstructured":"Schuller, B., Rigoll, G., & Lang, M. (2003). Hidden Markov model-based speech emotion recognition. In Proceedings of the IEEE international conference on acoustics, speech, and signal processing."},{"key":"9371_CR20","doi-asserted-by":"crossref","unstructured":"Sethu, V., Ambikairajah, E., & Epps, J. (2007). Speaker normalisation for speech-based emotion detection. In Procceedingsd of 15th international conference on digital signal processing, Cardiff (pp. 611\u2013614)","DOI":"10.1109\/ICDSP.2007.4288656"},{"key":"9371_CR21","unstructured":"Steidl, S. (2009). Automatic classification of emotion-related user states in spontaneous children\u2019s speech, PhD thesis, FAU Erlangen-Nuremberg."},{"key":"9371_CR22","doi-asserted-by":"crossref","unstructured":"Sukhummek, P., Kasuriya, S., Theeramunkong, T., et al. Feature selection experiments on emotional speech classification, In Proc. of 12th IEEE International Conference on Electrical Engineering\/Electronics, Computer, Telecommunications and Information Technology, pp.1-4 (2015).","DOI":"10.1109\/ECTICon.2015.7207122"},{"key":"9371_CR23","doi-asserted-by":"crossref","unstructured":"Tao, Y., Wang, K., Yang, J. et al. (2015). Harmony search for feature selection in speech emotion recognition, In Proceedings of the IEEE international conference on affective computing and intelligent interaction (ACII) (pp. 362\u2013367).","DOI":"10.1109\/ACII.2015.7344596"},{"key":"9371_CR24","unstructured":"Tato, R., Santos, R., Kompe, R., & Pardo, J. M. (2002). Emotional space improves emotion recognition, In Proceedings of the 6th IEEE international conference on spoken language processing, Denver, CO (pp. 2029\u20132032)."},{"key":"9371_CR25","unstructured":"Truong, K. P. (2009). How does real affect affect affect recognition in speech? PhD thesis, University of Twente."},{"key":"9371_CR26","unstructured":"Ververidis, D., & Kotropoulos, C. (2004). Automatic speech classification to five emotional states based on gender information. In Proceedings of the 12th European signal processing conference, Vienna (pp. 341\u2013344)."},{"key":"9371_CR27","first-page":"2249","volume-title":"Combining frame and turn-level information for robust recognition of emotions within speech","author":"B Vlasenko","year":"2007","unstructured":"Vlasenko, B., Schuller, B., Wendemuth, A., & Rigoll, G. (2007). Combining frame and turn-level information for robust recognition of emotions within speech (pp. 2249\u20132252). Brighton: In Proc. of Interspeech."},{"key":"9371_CR28","unstructured":"Vogt, T., & Andre, E. (2006). Improving automatic emotion recognition from speech via gender differentiation. In Proceedings of the 5th language resources and evaluation conference, Genoa."},{"key":"9371_CR29","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 interspeech, Pittsburgh, PA (pp. 2102\u20132105).","DOI":"10.21437\/Interspeech.2006-191"},{"key":"9371_CR30","doi-asserted-by":"crossref","first-page":"768","DOI":"10.1016\/j.specom.2010.08.013","volume":"53","author":"S Wu","year":"2011","unstructured":"Wu, S., Falk, T. H., & Chan, W. Y. (2011). Automatic speech emotion recognition using modulation spectral features. Speech Communication, 53, 768\u2013785.","journal-title":"Speech Communication"},{"key":"9371_CR31","first-page":"28","volume":"31","author":"L Zhao","year":"2006","unstructured":"Zhao, L., Wang, Z., & Zou, C. (2006). Emotional speech recognition based on modified parameter and distance of statistical model of pitch. Acta Acustica, 31, 28\u201334.","journal-title":"Acta Acustica"},{"key":"9371_CR32","doi-asserted-by":"crossref","unstructured":"Zou, C., Huang, C., Han, D., & Zhao, L. (2011). Detecting practical speech emotion in a cognitive task. In Proceedings of the of 20th computer communications and networks (Vol. 31), Maui, HI.","DOI":"10.1109\/ICCCN.2011.6005883"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-016-9371-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-016-9371-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-016-9371-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,19]],"date-time":"2024-06-19T18:26:38Z","timestamp":1718821598000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-016-9371-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10,1]]},"references-count":32,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2016,12]]}},"alternative-id":["9371"],"URL":"https:\/\/doi.org\/10.1007\/s10772-016-9371-3","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2016,10,1]]}}}