{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T09:55:02Z","timestamp":1780048502884,"version":"3.53.1"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2020,7,15]],"date-time":"2020-07-15T00:00:00Z","timestamp":1594771200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,7,15]],"date-time":"2020-07-15T00:00:00Z","timestamp":1594771200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["BCA150054"],"award-info":[{"award-number":["BCA150054"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100006525","name":"University of Southern Mississippi","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100006525","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":[[2020,9]]},"DOI":"10.1007\/s10772-020-09734-7","type":"journal-article","created":{"date-parts":[[2020,7,15]],"date-time":"2020-07-15T10:03:58Z","timestamp":1594807438000},"page":"633-642","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Significance of Phonological Features in Speech Emotion Recognition"],"prefix":"10.1007","volume":"23","author":[{"given":"Wei","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul A.","family":"Watters","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyi","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingjie","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3330-8103","authenticated-orcid":false,"given":"Bo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,7,15]]},"reference":[{"key":"9734_CR1","doi-asserted-by":"publisher","first-page":"30089","DOI":"10.1109\/ACCESS.2019.2902949","volume":"7","author":"AY Appiah","year":"2019","unstructured":"Appiah, A. Y., Zhang, X., Ayawli, B. B. K., & Kyeremeh, F. (2019). Long short-term memory networks based automatic feature extraction for photovoltaic array fault diagnosis. IEEE Access, 7, 30089\u201330101.","journal-title":"IEEE Access"},{"key":"9734_CR2","doi-asserted-by":"crossref","unstructured":"Badshah, A. M., Rahim, N., Ullah, N., Ahmad, J., Muhammad, K., Lee, M. Y., S. KwonSung, Baik, W. (2017). Deep features-based speech emotion recognition for smart affective services. Multimedia Tools and Applications, pp 1\u201319.","DOI":"10.1007\/s11042-017-5292-7"},{"key":"9734_CR3","doi-asserted-by":"crossref","unstructured":"Beckman, M. E., Hirschberg, J., & Shattuck-Hufnagel, S. (2005). The Original ToBI System and the Evolution of the ToBi Framework. Prosodic Typololgy: The Phonology of Intonation and Phrasing, pp. 9\u201354.","DOI":"10.1093\/acprof:oso\/9780199249633.003.0002"},{"issue":"2","key":"9734_CR4","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1007\/s10772-018-9498-5","volume":"21","author":"T Bhowmik","year":"2018","unstructured":"Bhowmik, T., & Mandal, S. K. D. (2018). Manner of articulation based Bengali phoneme classification. International Journal of Speech Technology, 21(2), 233\u2013250.","journal-title":"International Journal of Speech Technology"},{"issue":"4","key":"9734_CR5","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","volume":"42","author":"C Busso","year":"2008","unstructured":"Busso, C., Bulut, M., & Lee, C. C. (2008). IEMOCAP: Interactive emotional dyadic motion capture database. Language Resources and Evaluation, 42(4), 335.","journal-title":"Language Resources and Evaluation"},{"key":"9734_CR6","doi-asserted-by":"crossref","unstructured":"Cao, H. (2014). Prosodic cues for emotion: analysis with discrete characterization of intonation. Speech prosody. pp. 1147\u20131152.","DOI":"10.21437\/SpeechProsody.2014-14"},{"issue":"3","key":"9734_CR7","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1037\/0033-295X.99.3.550","volume":"99","author":"P Ekman","year":"1992","unstructured":"Ekman, P. (1992). Are there basic emotions? Psychological Review, 99(3), 550\u2013553.","journal-title":"Psychological Review"},{"key":"9734_CR8","doi-asserted-by":"crossref","unstructured":"Eyben, F. (2010). Opensmile: the munich versatile and fast open-source audio feature extractor. In ACM International Conference on Multimedia, pp. 1459\u20131462.","DOI":"10.1145\/1873951.1874246"},{"key":"9734_CR9","doi-asserted-by":"crossref","unstructured":"Fayek, H. M., Lech, M., & Cavedon, L. (2017). Evaluating deep learning architectures for Speech Emotion Recognition. Neural Networks, S089360801730059X.","DOI":"10.1016\/j.neunet.2017.02.013"},{"key":"9734_CR10","unstructured":"Fernandez, R. (2004). A computational model for the automatic recognition of affect in speech. Massachusetts Institute of Technology"},{"key":"9734_CR11","unstructured":"Han, W. J. (2014). Review on speech emotion recognition. Journal of Software."},{"issue":"5","key":"9734_CR12","doi-asserted-by":"publisher","first-page":"6785","DOI":"10.1007\/s11042-016-3354-x","volume":"76","author":"Z Huang","year":"2017","unstructured":"Huang, Z., Xue, W., Mao, Q., & Zhan, Y. (2017). Unsupervised domain adaptation for speech emotion recognition using PCANet. Multimedia Tools & Applications, 76(5), 6785\u20136799.","journal-title":"Multimedia Tools & Applications"},{"key":"9734_CR13","doi-asserted-by":"crossref","unstructured":"Iliev, A. I., Zhang, Y., & Scordilis, M. S. (2007). Spoken emotion classification using ToBI features and GMM. In International Workshop on Systems, Signals and Image Processing, 2007 and Eurasip Conference Focused on Speech and Image Processing, Multimedia Communications and Services, pp. 495\u2013498.","DOI":"10.1109\/IWSSIP.2007.4381149"},{"key":"9734_CR14","doi-asserted-by":"crossref","unstructured":"Jin, Q. Li, C., Chen, S. (2015). Speech emotion recognition with acoustic and lexical features. In IEEE International Conference on Acoustics, pp. 4749\u20134753","DOI":"10.1109\/ICASSP.2015.7178872"},{"issue":"9\u201310","key":"9734_CR15","doi-asserted-by":"publisher","first-page":"1162","DOI":"10.1016\/j.specom.2011.06.004","volume":"53","author":"CC Lee","year":"2011","unstructured":"Lee, C. C., Mower, E., & Busso, C. (2011). Emotion recognition using a hierarchical binary decision tree approach. Speech Communication, 53(9\u201310), 1162\u20131171.","journal-title":"Speech Communication"},{"issue":"2","key":"9734_CR16","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1109\/T-AFFC.2013.11","volume":"4","author":"S Mariooryad","year":"2013","unstructured":"Mariooryad, S., & Busso, C. (2013). Exploring cross-modality affective reactions for audiovisual emotion recognition. IEEE Transactions on Affective Computing, 4(2), 183\u2013196.","journal-title":"IEEE Transactions on Affective Computing"},{"key":"9734_CR17","doi-asserted-by":"crossref","unstructured":"Mirsamadi, S., Barsoum, E., Zhang, C. (2017). Automatic speech emotion recognition using recurrent neural networks with local attention. In IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 2227\u20132231.","DOI":"10.1109\/ICASSP.2017.7952552"},{"key":"9734_CR18","unstructured":"M\u00fcller, C. (2010). The INTERSPEECH 2010 paralinguistic challenge. INTERSPEECH 2010, Conference of the International Speech Communication Association, Makuhari, Chiba, Japan, September, pp. 2794\u20132797."},{"key":"9734_CR19","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1098\/rspl.1895.0041","volume":"58","author":"K Pearson","year":"1895","unstructured":"Pearson, K. (1895). Notes on regression and inheritance in the case of two parents. Proceedings of the Royal Society of London, 58, 240\u2013242.","journal-title":"Proceedings of the Royal Society of London"},{"key":"9734_CR20","doi-asserted-by":"crossref","unstructured":"Rosenberg, A. (2010). AuToBI\u2014A tool for automatic ToBI annotation. INTERSPEECH 2010, Conference of the International Speech Communication Association, Makuhari, Chiba, Japan, pp. 146\u2013149.","DOI":"10.21437\/Interspeech.2010-71"},{"key":"9734_CR21","unstructured":"Schr\u00f6der, M. (1992). ToBI: A standard for labeling English prosody. In International Conference on Spoken Language Processing, ICSLP 1992, Banff, Alberta, Canada."},{"key":"9734_CR22","doi-asserted-by":"crossref","unstructured":"Schuller, B., Steidl, S., & Batliner, A. (2009). The Interspeech 2009 Emotion Challenge. In INTERSPEECH 2009, Conference of the International Speech Communication Association, pp. 312\u2013315.","DOI":"10.21437\/Interspeech.2009-103"},{"key":"9734_CR23","doi-asserted-by":"crossref","unstructured":"Schuller, B., Vlasenko, B., & Eyben, F. (2009) Acoustic emotion recognition: A benchmark comparison of performances. In IEEE Workshop on Automatic Speech Recognition & Understanding. ASRU 2009, pp. 552\u2013557, 2009.","DOI":"10.1109\/ASRU.2009.5372886"},{"key":"9734_CR24","doi-asserted-by":"crossref","unstructured":"Shah, M., Chakrabarti, C., Spanias, A. (2014). A multi-modal approach to emotion recognition using undirected topic models. IEEE International Symposium on Circuits and Systems, pp. 754\u2013757,.","DOI":"10.1109\/ISCAS.2014.6865245"},{"key":"9734_CR25","unstructured":"Shen, L., & Wang, W. (2018). Improving speech emotion recognition based on tobi phonological representation. In PATTERNS 2018, The Tenth International Conference on Pervasive Patterns and Applications, pp.1\u20135."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-020-09734-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-020-09734-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-020-09734-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T20:56:16Z","timestamp":1667422576000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-020-09734-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,15]]},"references-count":25,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,9]]}},"alternative-id":["9734"],"URL":"https:\/\/doi.org\/10.1007\/s10772-020-09734-7","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7,15]]},"assertion":[{"value":"27 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}