{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T09:16:55Z","timestamp":1762507015513,"version":"3.37.3"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2017,2,21]],"date-time":"2017-02-21T00:00:00Z","timestamp":1487635200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100004608","name":"Jiangsu Province Natural Science Foundation","doi-asserted-by":"crossref","award":["BK20140649"],"award-info":[{"award-number":["BK20140649"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation","doi-asserted-by":"crossref","award":["no.61503081, no.61473079"],"award-info":[{"award-number":["no.61503081, no.61473079"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Wireless Pers Commun"],"published-print":{"date-parts":[[2017,8]]},"DOI":"10.1007\/s11277-017-4052-3","type":"journal-article","created":{"date-parts":[[2017,2,21]],"date-time":"2017-02-21T08:25:45Z","timestamp":1487665545000},"page":"2223-2238","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Novel Sub-band Spectral Centroid Weighted Wavelet Packet Features with Importance-Weighted Support Vector Machines for Robust Speech Emotion Recognition"],"prefix":"10.1007","volume":"95","author":[{"given":"Yongming","family":"Huang","sequence":"first","affiliation":[]},{"given":"Wu","family":"Ao","sequence":"additional","affiliation":[]},{"given":"Guobao","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,2,21]]},"reference":[{"issue":"1","key":"4052_CR1","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1109\/TPAMI.2008.52","volume":"31","author":"ZH Zeng","year":"2009","unstructured":"Zeng, Z. H., Pantic, M., Roisman, G. I., et al. (2009). A survey of affect recognition methods: audio, visual, and spontaneous expressions[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(1), 39\u201358.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"3","key":"4052_CR2","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1002\/imhj.21442","volume":"35","author":"J Brisson","year":"2014","unstructured":"Brisson, J., Martel, K., Serres, J., Sirois, S., & Adrien, J. L. (2014). Acoustic analysis of oral productions of infants later diagnosed with autism and their mother. Infant Mental Health Journal, 35(3), 285\u2013295.","journal-title":"Infant Mental Health Journal"},{"issue":"3","key":"4052_CR3","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1080\/10494820.2014.908927","volume":"24","author":"B Kiavash","year":"2016","unstructured":"Kiavash, B., Rob, N., & Wim, W. (2016). Towards multimodal emotion recognition in e-learning environments. Interactive Learning Environments, 24(3), 590\u2013605.","journal-title":"Interactive Learning Environments"},{"issue":"2","key":"4052_CR4","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1007\/s12369-015-0329-4","volume":"8","author":"J Crumpton","year":"2015","unstructured":"Crumpton, J., & Bethel, C. L. (2015). A survey of using vocal prosody to convey emotion in robot speech. International Journal of Social Robotics, 8(2), 271\u2013285.","journal-title":"International Journal of Social Robotics"},{"issue":"4","key":"4052_CR5","first-page":"183","volume":"10","author":"I Inshirah","year":"2015","unstructured":"Inshirah, I., & Salam, M. S. H. (2015). Voice quality features for speech emotion recognition. Journal of Information Assurance and Security, 10(4), 183\u2013191.","journal-title":"Journal of Information Assurance and Security"},{"issue":"2","key":"4052_CR6","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1109\/TSA.2004.838534","volume":"13","author":"CM Lee","year":"2005","unstructured":"Lee, C. M., & Narayanan, S. S. (2005). Toward detecting emotions in spoken dialogs[J]. IEEE Transactions on Speech and Audio Processing, 13(2), 293\u2013303.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"unstructured":"Schuller, B., Rigoll, G., & Lang, M. (2004). Speech emotion recognition combining acoustic features and linguistic information in a hybrid support vector machine-belief network architecture[C]\/\/Acoustics, Speech, and Signal Processing, 2004. In Proceedings. (ICASSP \u201804). IEEE International Conference on, 2004: I-577-580.","key":"4052_CR7"},{"unstructured":"Vlasenko, B., Schuller, B., Wendemuth, A. et al. (2007). Frame vs. turn-level: Emotion recognition from speech considering static and dynamic processing[C]\/\/Affective Computing and Intelligent Interaction, Proceedings, 2007: 139\u2013147, 781.","key":"4052_CR8"},{"issue":"6","key":"4052_CR9","doi-asserted-by":"crossref","first-page":"1304","DOI":"10.1121\/1.1914702","volume":"55","author":"BS Atal","year":"1974","unstructured":"Atal, B. S. (1974). Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification[J]. The Journal of the Acoustical Society of America, 55(6), 1304\u20131312.","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"1","key":"4052_CR10","doi-asserted-by":"crossref","first-page":"129.e1","DOI":"10.1016\/j.jvoice.2012.08.008","volume":"27","author":"M Guzman","year":"2013","unstructured":"Guzman, M., Correa, S., Munoz, D., et al. (2013). Influence on spectral energy distribution of emotional expression[J]. Journal of Voice, 27(1), 129.e1\u2013129.e10.","journal-title":"Journal of Voice"},{"key":"4052_CR11","volume-title":"Psychoacoustics: Facts and models[M]","author":"H Fastl","year":"1999","unstructured":"Fastl, H., & Zwicer, E. (1999). Psychoacoustics: Facts and models[M] (2nd ed.). New York: Springer-Verlag.","edition":"2"},{"key":"4052_CR12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2011\/624575","volume":"2011","author":"AI Iliev","year":"2011","unstructured":"Iliev, A. I., & Scordilis M. S. (2011). Spoken emotion recognition using glottal symmetry[J]. Eurasip Journal on Advances in Signal Processing, 2011(1), 1\u201311.","journal-title":"Eurasip Journal on Advances in Signal Processing"},{"issue":"7","key":"4052_CR13","doi-asserted-by":"crossref","first-page":"1458","DOI":"10.1109\/TASL.2013.2255278","volume":"21","author":"A Hassan","year":"2013","unstructured":"Hassan, A., Damper, R., & Niranjan, M. (2013). On acoustic emotion recognition: Compensating for covariate shift. IEEE Transactions on Audio, Speech and Language Processing, 21(7), 1458\u20131468.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"3","key":"4052_CR14","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1016\/j.specom.2007.01.006","volume":"49","author":"M Shamiand","year":"2007","unstructured":"Shamiand, M., & Verhelst, W. (2007). An evaluation of the robustness of existing supervised machine learning approaches to the classification of emotions in speech. Speech Communication, 49(3), 201\u2013212.","journal-title":"Speech Communication"},{"issue":"1","key":"4052_CR15","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1109\/TASLP.2015.2487051","volume":"24","author":"M Tahon","year":"2016","unstructured":"Tahon, M., & Devillers, L. (2016). Towards a small set of robust acoustic features for emotion recognition: Challenges. IEEE-ACM Transactions on Audio Speech and Language Processing, 24(1), 16\u201328.","journal-title":"IEEE-ACM Transactions on Audio Speech and Language Processing"},{"issue":"1","key":"4052_CR16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13636-014-0049-y","volume":"2015","author":"M Shah","year":"2015","unstructured":"Shah, M., Chakrabarti, C., & Spanias, A. (2015). Within and cross-corpus speech emotion recognition using latent topic model-based features. Eurasip Journal on Audio Speech and Music Processing, 2015(1), 1\u201317.","journal-title":"Eurasip Journal on Audio Speech and Music Processing"},{"doi-asserted-by":"crossref","unstructured":"Deng, J., Xia, R., Zhang, Z., & Liu, Y. (2014) Introducing shared-hidden-layer autoencoders for transfer learning and their application in acoustic emotion recognition. Icassp IEEE International Conference on Acoustics, 4818\u20134822.","key":"4052_CR17","DOI":"10.1109\/ICASSP.2014.6854517"},{"issue":"3","key":"4052_CR18","first-page":"547","volume":"31","author":"M Tahon","year":"2015","unstructured":"Tahon, M., Sehili, M. A., & Devillers, L. (2015). Cross-corpus experiments on laughter and emotion detection in HRI with elderly people. Springer International Publishing, 31(3), 547\u2013548.","journal-title":"Springer International Publishing"},{"issue":"1","key":"4052_CR19","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1049\/el.2014.3339","volume":"51","author":"P Song","year":"2015","unstructured":"Song, P., Jin, Y., Zha, C., & Zhao, L. (2015). Speech emotion recognition method based on hidden factor analysis. Electronics Letters, 51(1), 112\u2013114.","journal-title":"Electronics Letters"},{"key":"4052_CR20","volume-title":"A wavelet tour of signal processing[M]","author":"S Mallat","year":"2009","unstructured":"Mallat, S. (2009). A wavelet tour of signal processing[M] (3rd ed.). Burlington: Academic Press.","edition":"3"},{"doi-asserted-by":"crossref","unstructured":"Daubechies, I. (1992). Ten lectures on wavelets[M] Philadelphia: Society for industrial and applied mathematics.","key":"4052_CR21","DOI":"10.1137\/1.9781611970104"},{"issue":"7","key":"4052_CR22","doi-asserted-by":"crossref","first-page":"674","DOI":"10.1109\/34.192463","volume":"11","author":"SG Mallat","year":"1989","unstructured":"Mallat, S. G. (1989). A theory for multiresolution signal decomposition: the wavelet representation[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 11(7), 674\u2013693.","journal-title":"Pattern Analysis and Machine Intelligence, IEEE Transactions on"},{"key":"4052_CR23","volume-title":"Fundamentals of speech recognition[M]","author":"L Rabiner","year":"1993","unstructured":"Rabiner, L., & Juang, B.-H. (1993). Fundamentals of speech recognition[M]. New Jersey: Prentice-Hall."},{"issue":"4","key":"4052_CR24","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1109\/LSP.2006.884129","volume":"14","author":"A Karmakar","year":"2007","unstructured":"Karmakar, A., Kumar, A., & Patney, R. K. (2007). Design of optimal wavelet packet trees based on auditory perception criterion[J]. IEEE Signal Processing Letters, 14(4), 240\u2013243.","journal-title":"IEEE Signal Processing Letters"},{"doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, G, & Huang, Y. (2013). Adaptive wavelet packet filter-bank based acoustic feature for speech emotion recognition[C]. In Proceedings of 2013 Chinese Intelligent Automation Conference-Intelligent Information Processing. Heidelberg: Springer Verlag, pp. 359\u2013366.","key":"4052_CR25","DOI":"10.1007\/978-3-642-38466-0_40"},{"issue":"5","key":"4052_CR26","doi-asserted-by":"crossref","first-page":"768","DOI":"10.1016\/j.specom.2010.08.013","volume":"53","author":"SQ Wu","year":"2011","unstructured":"Wu, S. Q., Falk, T. H., & Chan, W. Y. (2011). Automatic speech emotion recognition using modulation spectral features[J]. Speech Communication, 53(5), 768\u2013785.","journal-title":"Speech Communication"},{"issue":"14","key":"4052_CR27","doi-asserted-by":"crossref","first-page":"e49","DOI":"10.1093\/bioinformatics\/btl242","volume":"22","author":"KM Borgwardt","year":"2006","unstructured":"Borgwardt, K. M., Gretton, A., Rasch, M. J., Kriegel, H.-P., & Smola, A. J. (2006). Integrating structured biological data by kernel maximum mean discrepancy. Bioinfor-matics, 22(14), e49\u2013e57.","journal-title":"Bioinfor-matics"},{"unstructured":"Hido, S., Tsuboi, Y., Kashima, H., & Sugiyama, M. (2007). Novelty detection by density ratio estimation. In Proceedings of IBIS.","key":"4052_CR28"},{"doi-asserted-by":"crossref","unstructured":"Mozafari, A. S., & Amzad, M. (2016). A SVM-based model-transferring method for heterogeneous domain adaptation. Pattern Recognition, 56, 142\u2013158.","key":"4052_CR29","DOI":"10.1016\/j.patcog.2016.03.009"},{"unstructured":"Burkhardt, F., Paeschke, A., Rolfes, M. et al. (2005). A database of German emotional speech[C]\/\/Proceeding INTERSPEECH 2005, pp. 1517\u20131520.","key":"4052_CR30"}],"container-title":["Wireless Personal Communications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11277-017-4052-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11277-017-4052-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11277-017-4052-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,18]],"date-time":"2019-09-18T18:49:00Z","timestamp":1568832540000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11277-017-4052-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,2,21]]},"references-count":30,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2017,8]]}},"alternative-id":["4052"],"URL":"https:\/\/doi.org\/10.1007\/s11277-017-4052-3","relation":{},"ISSN":["0929-6212","1572-834X"],"issn-type":[{"type":"print","value":"0929-6212"},{"type":"electronic","value":"1572-834X"}],"subject":[],"published":{"date-parts":[[2017,2,21]]}}}