{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T23:13:58Z","timestamp":1742944438023,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030234065"},{"type":"electronic","value":"9783030234072"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-23407-2_10","type":"book-chapter","created":{"date-parts":[[2019,6,18]],"date-time":"2019-06-18T12:03:10Z","timestamp":1560859390000},"page":"117-131","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Speech Emotion Recognition Using Multi-granularity Feature Fusion Through Auditory Cognitive Mechanism"],"prefix":"10.1007","author":[{"given":"Cong","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haifeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongjian","family":"Bo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,6,19]]},"reference":[{"key":"10_CR1","volume-title":"The Cognitive Structure of Emotions","author":"A Ortony","year":"1990","unstructured":"Ortony, A., Clore, G.L., Collins, A.: The Cognitive Structure of Emotions. Cambridge Univ Pr, Cambridge (1990)"},{"issue":"1","key":"10_CR2","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1016\/S0167-6393(02)00084-5","volume":"40","author":"KR Scherer","year":"2003","unstructured":"Scherer, K.R.: Vocal communication of emotion: a review of research paradigms. Speech Commun. 40(1), 227\u2013256 (2003)","journal-title":"Speech Commun."},{"issue":"1","key":"10_CR3","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1016\/j.csl.2013.07.002","volume":"28","author":"JP Arias","year":"2014","unstructured":"Arias, J.P.: Shape-based modeling of the fundamental frequency contour for emotion detection in speech. Comput. Speech Lang. 28(1), 278\u2013294 (2014)","journal-title":"Comput. Speech Lang."},{"issue":"5","key":"10_CR4","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1109\/LSP.2014.2311435","volume":"21","author":"L Zao","year":"2014","unstructured":"Zao, L.: Time-Frequency feature and AMS-GMM mask for acoustic emotion classification. IEEE Signal Process. Lett. 21(5), 620\u2013624 (2014)","journal-title":"IEEE Signal Process. Lett."},{"key":"10_CR5","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1016\/j.knosys.2014.03.019","volume":"63","author":"A Mencatini","year":"2014","unstructured":"Mencatini, A., Martineli, E., Costantini, G., et al.: Speech emotion recognition using amplitude modulation parameters and a combined feature selection procedure. Knowl-Based Syst. 63, 68\u201381 (2014)","journal-title":"Knowl-Based Syst."},{"key":"10_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"706","DOI":"10.1007\/978-3-319-09333-8_77","volume-title":"Intelligent Computing Theory","author":"Y Huang","year":"2014","unstructured":"Huang, Y., Zhang, G., Li, Y., Wu, A.: Improved emotion recognition with novel task-oriented wavelet packet features. In: Huang, D.-S., Bevilacqua, V., Premaratne, P. (eds.) ICIC 2014. LNCS, vol. 8588, pp. 706\u2013714. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-09333-8_77"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Ziolko, M., Jaciow, P., Igras, M.: Combination of Fourier and wavelet transformations for detection of speech emotions. In: 7th International Conference on Human System Interactions (HSI), pp. 49\u201354. IEEE (2014)","DOI":"10.1109\/HSI.2014.6860447"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Idris, I., Salam, M.S.H.: Emotion detection with hybrid voice quality and prosodic features using neural network. In: 2014 Fourth World Congress on Information and Communication Technologies (WICT), pp. 205\u2013210. IEEE (2014)","DOI":"10.1109\/WICT.2014.7076906"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Kachele, M., Zharkov, D., Meudt, S., et al.: Prosodic, spectral and voice quality features selection using a long-term stopping criterion for audio-based emotion recognition. In: 2nd International Conference on Pattern Recognition (ICPR), pp. 803\u2013808. IEEE (2014)","DOI":"10.1109\/ICPR.2014.148"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Sepp\u00e4nen, T., V\u00e4yrynen, E., Toivanen, J.: Prosody-based classification of emotions in spoken finnish. In: Proceedings the 2003 European Conference on Speech Communication and Technology. EUROSPEECH, pp. 717\u2013720. ISCA, Geneva (2003)","DOI":"10.21437\/Eurospeech.2003-304"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Li, X., Tao, J., Johnson, M.T., et al.: Stress and emotion classification using jitter and shimmer features. In: Proceedings the 2007 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), IV, pp. 1081\u20131084. IEEE, Honolulu (2007)","DOI":"10.1109\/ICASSP.2007.367261"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"He, L., Lechm, M., Allen, N.: On the importance of glottal flow spectral energy for the recognition of emotions in speech. In: Proceedings the 2010 INTERSPEECH, pp. 2346\u20132349. ISCA, Chiba (2010)","DOI":"10.21437\/Interspeech.2010-642"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Sanchez, M.H., Vergyri, D., Ferrer, L., et al.: Using prosodic and spectral features in detecting depression in elderly males. In: Proceedings the 2011 INTERSPEECH, pp. 3001\u20133004. ISCA, Florence (2011)","DOI":"10.21437\/Interspeech.2011-751"},{"issue":"1","key":"10_CR14","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1001\/jama.1964.03070010021004","volume":"189","author":"RH Rosenman","year":"1964","unstructured":"Rosenman, R.H.: A predictive study of coronary heart disease: the western collaborative group study. JAMA 189(1), 15\u201322 (1964)","journal-title":"JAMA"},{"issue":"3","key":"10_CR15","first-page":"374","volume":"33","author":"C Jing","year":"2017","unstructured":"Jing, C., Haifeng, L., Lin, Ma., et al.: Multi-granularity feature fusion for dimensional speech emotion recognition. J. Sig. Process. 33(3), 374\u2013382 (2017)","journal-title":"J. Sig. Process."},{"issue":"1","key":"10_CR16","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., et al.: Emotion recognition in human computer interaction. IEEE Signal Process. Mag. 18(1), 32\u201380 (2001)","journal-title":"IEEE Signal Process. Mag."},{"issue":"2","key":"10_CR17","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1121\/1.405558","volume":"93","author":"I Murray","year":"1993","unstructured":"Murray, I., Arnott, J.: Toward a simulation of emotion in synthetic speech: a review of the literature on human vocal emotion. J. Acoust. Soc. Am. 93(2), 1097\u20131108 (1993)","journal-title":"J. Acoust. Soc. Am."},{"issue":"3","key":"10_CR18","first-page":"423","volume":"30","author":"Z Li","year":"2004","unstructured":"Li, Z., Zhiping, W., Wei, L., Cairong, Z., Zhenyang, W.: Speech emotional recognition using global and time sequence structure feature. Acta Automatica Sinica 30(3), 423\u2013429 (2004)","journal-title":"Acta Automatica Sinica"},{"issue":"1","key":"10_CR19","first-page":"37","volume":"25","author":"H Wenjing","year":"2014","unstructured":"Wenjing, H., Haifeng, L., Huabin, R., et al.: Review on speech emotion recognition. J. Softw. 25(1), 37\u201350 (2014)","journal-title":"J. Softw."},{"issue":"12","key":"10_CR20","doi-asserted-by":"publisher","first-page":"2653","DOI":"10.1097\/00001756-200108280-00013","volume":"12","author":"DA Levy","year":"2001","unstructured":"Levy, D.A., Granot, R., Bentin, S.: Processing specificity for human voice stimuli: electrophysiological evidence. NeuroReport 12(12), 2653\u20132657 (2001)","journal-title":"NeuroReport"},{"issue":"4","key":"10_CR21","doi-asserted-by":"publisher","first-page":"1293","DOI":"10.1523\/JNEUROSCI.4511-05.2006","volume":"26","author":"MM Murray","year":"2006","unstructured":"Murray, M.M., Camen, C., Gonzalez Andino, S.L., et al.: Rapid brain discrimination of sounds of objects. J. Neurosci. 26(4), 1293\u20131302 (2006)","journal-title":"J. Neurosci."},{"key":"10_CR22","first-page":"667","volume-title":"Communications in Computer and Information Science","author":"Ya Li","year":"2016","unstructured":"Li, Y., Tao, J., Schuller, B., Shan, S., Jiang, D., Jiam, J.: MEC 2016: the multimodal emotion recognition challenge of CCPR 2016. In: Chinese Conference on Pattern Recognition (CCPR), Chengdu (2016)"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Eyben, F., Weninger, F., Gross, F., Schuller, B.: Recent developments in openSMILE, the Munich open-source multimedia feature extractor. In: Proceedings of the 21st ACM International Conference on Multimedia, pp. 835\u2013838 (2013)","DOI":"10.1145\/2502081.2502224"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Schuller, B., et al.: The INTERSPEECH 2016 computational paralinguistics challenge: Deception, sincerity & native language. In: INTERSPEECH, pp. I\u2013I. ISCA (2016)","DOI":"10.21437\/Interspeech.2016-129"},{"key":"10_CR25","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"721","DOI":"10.1007\/978-981-10-3005-5_59","volume-title":"Pattern Recognition","author":"Y Huang","year":"2016","unstructured":"Huang, Y., Hu, M., Yu, X., Wang, T., Yang, C.: Transfer learning of deep neural network for speech emotion recognition. In: Tan, T., Li, X., Chen, X., Zhou, J., Yang, J., Cheng, H. (eds.) CCPR 2016. CCIS, vol. 663, pp. 721\u2013729. Springer, Singapore (2016). https:\/\/doi.org\/10.1007\/978-981-10-3005-5_59"}],"container-title":["Lecture Notes in Computer Science","Cognitive Computing \u2013 ICCC 2019"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-23407-2_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,21]],"date-time":"2022-09-21T01:20:57Z","timestamp":1663723257000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-23407-2_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030234065","9783030234072"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-23407-2_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"19 June 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Cognitive Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"San Diego, CA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 June 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 June 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccc2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/thecognitivecomputing.org\/2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}