{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,19]],"date-time":"2026-04-19T06:37:17Z","timestamp":1776580637411,"version":"3.51.2"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2019,9,6]],"date-time":"2019-09-06T00:00:00Z","timestamp":1567728000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,9,6]],"date-time":"2019-09-06T00:00:00Z","timestamp":1567728000000},"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":["Int J Speech Technol"],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1007\/s10772-019-09628-3","type":"journal-article","created":{"date-parts":[[2019,9,6]],"date-time":"2019-09-06T14:20:19Z","timestamp":1567779619000},"page":"865-884","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Segment based emotion recognition using combined reduced features"],"prefix":"10.1007","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1252-949X","authenticated-orcid":false,"given":"Mihir Narayan","family":"Mohanty","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hemanta Kumar","family":"Palo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,9,6]]},"reference":[{"issue":"1","key":"9628_CR1","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/S1018-3639(18)30850-X","volume":"19","author":"AI Al-Shoshan","year":"2006","unstructured":"Al-Shoshan, A. I. (2006). Speech and music classification and separation: A review. Journal of King Saud University,19(1), 95\u2013133.","journal-title":"Journal of King Saud University"},{"key":"9628_CR2","unstructured":"Bhattacharjee, D., Basu, D. K., Nasipuri, M., & Kundu, M. (2010). Reduction of feature vectors using rough set theory for human face recognition.\u00a0CoRR abs\/1005 (pp. 40\u201344)"},{"issue":"7","key":"9628_CR3","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1016\/j.specom.2010.02.010","volume":"52","author":"D Bitouk","year":"2010","unstructured":"Bitouk, D., Verma, R., & Nenkova, A. (2010). Class-level spectral features for emotion recognition. Speech Communication,52(7), 613\u2013625.","journal-title":"Speech Communication"},{"key":"9628_CR4","doi-asserted-by":"crossref","unstructured":"Burkhardt, F., Paeschke, A., Rolfes, M., Sendlmeier, W. F., & Weiss, B. (2005). A database of German emotional speech. In\u00a0Ninth European Conference on Speech Communication and Technology, Interspeech, (pp. 1517\u20131520).","DOI":"10.21437\/Interspeech.2005-446"},{"issue":"7\/8","key":"9628_CR5","first-page":"724","volume":"52","author":"JJ Burred","year":"2004","unstructured":"Burred, J. J., & Lerch, A. (2004). Hierarchical automatic audio signal classification. Journal of the Audio Engineering Society,52(7\/8), 724\u2013739.","journal-title":"Journal of the Audio Engineering Society"},{"key":"9628_CR6","doi-asserted-by":"crossref","unstructured":"Chiou, B. C., & Chen, C. P. (2013, October). Feature space dimension reduction in speech emotion recognition using support vector machine. In\u00a0Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2013 Asia-Pacific\u00a0(pp. 1\u20136). IEEE.","DOI":"10.1109\/APSIPA.2013.6694251"},{"issue":"5","key":"9628_CR7","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1002\/ima.20059","volume":"15","author":"K Delac","year":"2005","unstructured":"Delac, K., Grgic, M., & Grgic, S. (2005). Independent comparative study of PCA, ICA, and LDA on the FERET data set. International Journal of Imaging Systems and Technology,15(5), 252\u2013260.","journal-title":"International Journal of Imaging Systems and Technology"},{"key":"9628_CR8","doi-asserted-by":"crossref","unstructured":"Fewzee, P., & Karray, F. (2012). Dimensionality reduction for emotional speech recognition. In\u00a0Privacy, Security, Risk and Trust (PASSAT), 2012 International Conference on and 2012 International Conference on Social Computing (SocialCom)\u00a0(pp. 532\u2013537). IEEE.","DOI":"10.1109\/SocialCom-PASSAT.2012.83"},{"key":"9628_CR9","doi-asserted-by":"crossref","unstructured":"Gamage, K. W., Sethu, V., Le, P. N., & Ambikairajah, E. (2015, December). An i-vector GPLDA system for speech based emotion recognition. In\u00a0Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2015 Asia-Pacific\u00a0(pp. 289\u2013292). IEEE.","DOI":"10.1109\/APSIPA.2015.7415522"},{"issue":"9","key":"9628_CR10","first-page":"8","volume":"6","author":"J Gomes","year":"2016","unstructured":"Gomes, J., & El-Sharkawy, M. (2016). Implementation of i-vector algorithm in speech emotion recognition by using two different classifiers: Gaussian mixture model and support vector machine. International Journal of Advanced Research in Computer Science and Software Engineering,6(9), 8\u201316.","journal-title":"International Journal of Advanced Research in Computer Science and Software Engineering"},{"key":"9628_CR11","unstructured":"Haq, S., & Jackson, P. J. (2010). Multimodal emotion recognition.\u00a0In Machine audition: Principles, algorithms and systems, 398\u2013423."},{"key":"9628_CR12","volume-title":"Neural networks: A comprehensive foundation","author":"S Haykins","year":"2006","unstructured":"Haykins, S. (2006). Neural networks: A comprehensive foundation (2nd ed.). Delhi, India: Pearson Education.","edition":"2"},{"key":"9628_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, J., Wu, Z., Xu, M., Jia, J., & Cai, L. (2013). Comparing feature dimension reduction algorithms for GMM-SVM based speech emotion recognition. In\u00a0Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2013 Asia-Pacific\u00a0(pp. 1\u20134). IEEE.","DOI":"10.1109\/APSIPA.2013.6694336"},{"issue":"1","key":"9628_CR14","first-page":"111","volume":"1","author":"R Kaushik","year":"2016","unstructured":"Kaushik, R., Sharma, M., Sarma, K. K., & Kaplun, D. I. (2016). I-vector based emotion recognition in assamese speech. International Journal of Engineering and Future Technology,1(1), 111\u2013124.","journal-title":"International Journal of Engineering and Future Technology"},{"key":"9628_CR15","doi-asserted-by":"crossref","unstructured":"Khanna, P., & Kumar, M. S. (2011). Application of vector quantization in emotion recognition from human speech. In\u00a0International conference on information intelligence, systems, technology and management\u00a0(pp. 118\u2013125). Springer, Berlin, Heidelberg.","DOI":"10.1007\/978-3-642-19423-8_13"},{"issue":"1","key":"9628_CR16","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1007\/s10772-018-9495-8","volume":"21","author":"SG Koolagudi","year":"2018","unstructured":"Koolagudi, S. G., Murthy, Y. S., & Bhaskar, S. P. (2018). Choice of a classifier, based on properties of a dataset: Case study-speech emotion recognition. International Journal of Speech Technology,21(1), 167\u2013183.","journal-title":"International Journal of Speech Technology"},{"key":"9628_CR17","doi-asserted-by":"crossref","unstructured":"Lopez-Otero, P., Dacia-Fernandez, L., & Garcia-Mateo, C. (2014). A study of acoustic features for depression detection. In\u00a02014 International Workshop on\u00a0Biometrics and Forensics (IWBF) (pp. 1\u20136). IEEE.","DOI":"10.1109\/IWBF.2014.6914245"},{"issue":"3","key":"9628_CR18","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1109\/TBME.2010.2091640","volume":"58","author":"LSA Low","year":"2011","unstructured":"Low, L. S. A., Maddage, N. C., Lech, M., Sheeber, L. B., & Allen, N. B. (2011). Detection of clinical depression in adolescents\u2019 speech during family interactions. IEEE Transactions on Biomedical Engineering,58(3), 574\u2013586.","journal-title":"IEEE Transactions on Biomedical Engineering"},{"issue":"4","key":"9628_CR19","doi-asserted-by":"publisher","first-page":"1009","DOI":"10.1109\/72.857781","volume":"11","author":"KZ Mao","year":"2000","unstructured":"Mao, K. Z., Tan, K. C., & Ser, W. (2000). Probabilistic neural-network structure determination for pattern classification. IEEE Transactions on Neural Networks,11(4), 1009\u20131016.","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"2","key":"9628_CR20","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1109\/34.908974","volume":"23","author":"AM Mart\u00ednez","year":"2001","unstructured":"Mart\u00ednez, A. M., & Kak, A. C. (2001). Pca versus lda. IEEE Transactions on Pattern Analysis and Machine Intelligence,23(2), 228\u2013233.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"9628_CR21","doi-asserted-by":"crossref","unstructured":"Mohanty, M. N., & Routray, A. (2015). Machine learning approach for emotional speech classification. Springer International Publishing Switzerland 2015, SEMCCO 2014, LNCS 8947, Chap. 43 (pp. 1\u201312).","DOI":"10.1007\/978-3-319-20294-5_43"},{"issue":"07","key":"9628_CR22","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1142\/S0218001402002003","volume":"16","author":"P Navarrete","year":"2002","unstructured":"Navarrete, P., & Ruiz-del-Solar, J. (2002). Analysis and comparison of eigenspace-based face recognition approaches. International Journal of Pattern Recognition and Artificial Intelligence,16(07), 817\u2013830.","journal-title":"International Journal of Pattern Recognition and Artificial Intelligence"},{"issue":"2","key":"9628_CR23","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1109\/TBME.2012.2228646","volume":"60","author":"KEB Ooi","year":"2013","unstructured":"Ooi, K. E. B., Lech, M., & Allen, N. B. (2013). Multichannel weighted speech classification system for prediction of major depression in adolescents. IEEE Trans. Biomed. Engineering,60(2), 497\u2013506.","journal-title":"IEEE Trans. Biomed. Engineering"},{"key":"9628_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.asej.2016.11.001","author":"HK Palo","year":"2017","unstructured":"Palo, H. K., & Mohanty, M. N. (2017). Wavelet based feature combination for recognition of emotions. Ain Shams Engineering Journal. https:\/\/doi.org\/10.1016\/j.asej.2016.11.001 .","journal-title":"Ain Shams Engineering Journal"},{"issue":"1","key":"9628_CR27","doi-asserted-by":"publisher","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"},{"issue":"11","key":"9628_CR28","doi-asserted-by":"publisher","first-page":"2108","DOI":"10.1109\/TASLP.2016.2593944","volume":"24","author":"S Parthasarathy","year":"2016","unstructured":"Parthasarathy, S., Cowie, R., & Busso, C. (2016). Using agreement on direction of change to build rank-based emotion classifiers. IEEE\/ACM Transactions on Audio, Speech, and Language Processing,24(11), 2108\u20132121.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"issue":"5","key":"9628_CR29","doi-asserted-by":"publisher","first-page":"2902","DOI":"10.1121\/1.3642604","volume":"130","author":"G Peeters","year":"2011","unstructured":"Peeters, G., Giordano, B. L., Susini, P., Misdariis, N., & McAdams, S. (2011). The timbre toolbox: Extracting audio descriptors from musical signals. The Journal of the Acoustical Society of America,130(5), 2902\u20132916.","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"1","key":"9628_CR30","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/1687-4722-2013-8","volume":"2013","author":"J P\u0159ibil","year":"2013","unstructured":"P\u0159ibil, J., & P\u0159ibilov\u00e1, A. (2013). Evaluation of influence of spectral and prosodic features on GMM classification of Czech and Slovak emotional speech. EURASIP Journal on Audio, Speech, and Music Processing,2013(1), 8. https:\/\/doi.org\/10.1186\/1687-4722-2013-8 .","journal-title":"EURASIP Journal on Audio, Speech, and Music Processing"},{"key":"9628_CR31","doi-asserted-by":"crossref","unstructured":"Quan, C., Wan, D., Zhang, B., & Ren, F. (2013, December). Reduce the dimensions of emotional features by principal component analysis for speech emotion recognition. In\u00a02013 IEEE\/SICE International Symposium on\u00a0System Integration (SII) (pp. 222\u2013226). IEEE.","DOI":"10.1109\/SII.2013.6776653"},{"issue":"4","key":"9628_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1177\/1729881417719836","volume":"14","author":"C Quan","year":"2017","unstructured":"Quan, C., Zhang, B., Sun, X., & Ren, F. (2017). A combined cepstral distance method for emotional speech recognition. International Journal of Advanced Robotic Systems,14(4), 1\u20139.","journal-title":"International Journal of Advanced Robotic Systems"},{"issue":"1\u20132","key":"9628_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2000000001","volume":"1","author":"LR Rabiner","year":"2007","unstructured":"Rabiner, L. R., & Schafer, R. W. (2007). Introduction to digital speech processing. Foundations and Trends in Signal Processing,1(1\u20132), 1\u2013194.","journal-title":"Foundations and Trends in Signal Processing"},{"key":"9628_CR34","doi-asserted-by":"crossref","unstructured":"Schuller, B., Valstar, M., Eyben, F., McKeown, G., Cowie, R., & Pantic, M. (2011). Avec 2011\u2013the first international audio\/visual emotion challenge. In\u00a0Affective Computing and Intelligent Interaction\u00a0(pp. 415\u2013424). Springer, Berlin, Heidelberg.","DOI":"10.1007\/978-3-642-24571-8_53"},{"key":"9628_CR35","volume-title":"Principle of soft computing","author":"SN Sivanandam","year":"2011","unstructured":"Sivanandam, S. N., & Deepa, D. S. (2011). Principle of soft computing (2nd ed.). India: Wiley.","edition":"2"},{"key":"9628_CR36","first-page":"203","volume":"2","author":"DF Specht","year":"1994","unstructured":"Specht, D. F., & Romsdahl, H. (1994). Experience with adaptive probabilistic neural network and adaptive general regression neural network. IEEE\/INNS International Joint Conference, Neural Network,2, 203\u20131208.","journal-title":"IEEE\/INNS International Joint Conference, Neural Network"},{"key":"9628_CR37","doi-asserted-by":"publisher","DOI":"10.26717\/BJSTR.2018.05.001156","author":"MN Stolar","year":"2018","unstructured":"Stolar, M. N., Lech, M., Stolar, S. J., & Allen, N. B. (2018). Detection of adolescent depression from speech using optimised spectral roll-off parameters. Biomedical Journal of Scientific & Technical Research. https:\/\/doi.org\/10.26717\/BJSTR.2018.05.001156 .","journal-title":"Biomedical Journal of Scientific & Technical Research"},{"key":"9628_CR38","doi-asserted-by":"crossref","unstructured":"Tao, Y., Wang, K., Yang, J., An, N., & Li, L. (2015). Harmony search for feature selection in speech emotion recognition. In\u00a02015 International Conference on\u00a0Affective Computing and Intelligent Interaction (ACII) (pp. 362\u2013367). IEEE.","DOI":"10.1109\/ACII.2015.7344596"},{"key":"9628_CR39","doi-asserted-by":"crossref","unstructured":"Wang, K., An, N., & Li, L. (2014). Speech emotion recognition based on wavelet packet coefficient model. In\u00a02014 9th International Symposium on\u00a0Chinese Spoken Language Processing (ISCSLP) (pp. 478\u2013482). IEEE.","DOI":"10.1109\/ISCSLP.2014.6936710"},{"issue":"1","key":"9628_CR40","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1109\/TAFFC.2015.2392101","volume":"6","author":"K Wang","year":"2015","unstructured":"Wang, K., An, N., Li, B. N., & Zhang, Y. (2015). Speech emotion recognition using Fourier parameters. IEEE Transaction on Affective Computing,6(1), 69\u201375.","journal-title":"IEEE Transaction on Affective Computing"},{"key":"9628_CR41","doi-asserted-by":"crossref","unstructured":"Wenjing, H., Haifeng, L., & Chunyu, G. (2009). A hybrid speech emotion perception method of VQ-based feature processing and ANN recognition. In\u00a0WRI Global Congress on\u00a0Intelligent Systems, 2009. GCIS\u201909 (Vol. 2, pp. 145\u2013149). IEEE.","DOI":"10.1109\/GCIS.2009.432"},{"key":"9628_CR42","doi-asserted-by":"publisher","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, Elsevier,53, 768\u2013785.","journal-title":"Speech Communication, Elsevier"},{"key":"9628_CR43","doi-asserted-by":"crossref","unstructured":"Xu, X., Deng, J., Zheng, W., Zhao, L., & Schuller, B. (2015). Dimensionality reduction for speech emotion features by multiscale kernels. In\u00a0Sixteenth Annual Conference of the International Speech Communication Association, Interspeech 2015 (pp. 1532\u20131536)","DOI":"10.21437\/Interspeech.2015-335"},{"issue":"11","key":"9628_CR44","doi-asserted-by":"publisher","first-page":"299","DOI":"10.14257\/ijsip.2015.8.11.27","volume":"8","author":"J Yuan","year":"2015","unstructured":"Yuan, J., Chen, L., Fan, T., & Jia, J. (2015). Dimension reduction of speech emotion feature based on weighted linear discriminant analysis. International Journal of Signal Processing, Image Processing and Pattern Recognition,8(11), 299\u2013308.","journal-title":"International Journal of Signal Processing, Image Processing and Pattern Recognition"},{"issue":"3","key":"9628_CR45","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1037\/0033-2909.99.3.432","volume":"99","author":"WR Zwick","year":"1986","unstructured":"Zwick, W. R., & Velicer, W. F. (1986). Comparison of five rules for determining the number of components to retain. Psychological Bulletin,99(3), 432.","journal-title":"Psychological Bulletin"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-019-09628-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-019-09628-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-019-09628-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T19:20:21Z","timestamp":1664306421000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-019-09628-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,6]]},"references-count":43,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["9628"],"URL":"https:\/\/doi.org\/10.1007\/s10772-019-09628-3","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,9,6]]},"assertion":[{"value":"10 May 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 August 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 September 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}