{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T06:24:49Z","timestamp":1750832689636,"version":"3.37.3"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T00:00:00Z","timestamp":1723075200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T00:00:00Z","timestamp":1723075200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1007\/s00034-024-02817-9","type":"journal-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T07:02:15Z","timestamp":1723100535000},"page":"7843-7866","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Novel SEGAA: A Unified Approach to Predicting Age, Gender, and Emotion in Speech"],"prefix":"10.1007","volume":"43","author":[{"given":"Aron","family":"Ritesh","sequence":"first","affiliation":[]},{"given":"Indra Kiran","family":"Sigicharla","sequence":"additional","affiliation":[]},{"given":"Chirag","family":"Periwal","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3938-7495","authenticated-orcid":false,"given":"Mohanaprasad","family":"Kothandaraman","sequence":"additional","affiliation":[]},{"given":"P. S. Nithya","family":"Darisini","sequence":"additional","affiliation":[]},{"given":"Sourabh","family":"Tiwari","sequence":"additional","affiliation":[]},{"given":"Shivani","family":"Arora","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,8]]},"reference":[{"key":"2817_CR1","doi-asserted-by":"publisher","first-page":"119633","DOI":"10.1016\/j.eswa.2023.119633","volume":"218","author":"MR Ahmed","year":"2023","unstructured":"M.R. Ahmed, S. Islam, A.M. Islam, S. Shatabda, An ensemble 1D-CNN-LSTM-GRU model with data augmentation for speech emotion recognition. Expert Syst. Appl. 218, 119633 (2023)","journal-title":"Expert Syst. Appl."},{"key":"2817_CR2","unstructured":"F. Albu, D. Hagiescu, L. Vladutu, & M. A. Puica, Neural network approaches for children's emotion recognition in intelligent learning applications. In EDULEARN15 Proceedings pp. 3229\u20133239. IATED. (2015)"},{"key":"2817_CR3","first-page":"06670","volume-title":"2019","author":"R Ardila","year":"1912","unstructured":"R. Ardila, M. Branson, K. Davis, M. Henretty, M. Kohler, J. Meyer, R. Morais, L. Saunders, F.M. Tyers, G. Weber, G. Weber, 2019 (A massively-multilingual speech corpus. arXiv preprint arXiv, Common voice, 1912), p.06670"},{"issue":"1","key":"2817_CR4","doi-asserted-by":"publisher","first-page":"101","DOI":"10.3390\/su14010101","volume":"14","author":"RM B\u0103d\u00eercea","year":"2021","unstructured":"R.M. B\u0103d\u00eercea, A.G. Manta, N.M. Florea, J. Popescu, F.L. Manta, S. Puiu, E-commerce and the factors affecting its development in the age of digital technology: empirical evidence at EU\u201327 level. Sustainability 14(1), 101 (2021)","journal-title":"Sustainability"},{"key":"2817_CR5","first-page":"1517","volume":"5","author":"F Burkhardt","year":"2005","unstructured":"F. Burkhardt, A. Paeschke, M. Rolfes, W.F. Sendlmeier, B. Weiss, A database of German emotional speech. In Interspeech 5, 1517\u20131520 (2005)","journal-title":"In Interspeech"},{"key":"2817_CR6","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","volume":"42","author":"C Busso","year":"2008","unstructured":"C. Busso, M. Bulut, C.C. Lee, A. Kazemzadeh, E. Mower, S. Kim, S.S. Narayanan, IEMOCAP: Interactive emotional dyadic motion capture database. Lang. Resour. Eval. 42, 335\u2013359 (2008)","journal-title":"Lang. Resour. Eval."},{"key":"2817_CR7","doi-asserted-by":"publisher","first-page":"102481","DOI":"10.1016\/j.jretconser.2021.102481","volume":"60","author":"S Cachero-Mart\u00ednez","year":"2021","unstructured":"S. Cachero-Mart\u00ednez, R. V\u00e1zquez-Casielles, Building consumer loyalty through e-shopping experiences: The mediating role of emotions. J. Retail. Consum. Serv. 60, 102481 (2021)","journal-title":"J. Retail. Consum. Serv."},{"issue":"4","key":"2817_CR8","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1109\/TAFFC.2014.2336244","volume":"5","author":"H Cao","year":"2014","unstructured":"H. Cao, D.G. Cooper, M.K. Keutmann, R.C. Gur, A. Nenkova, R. Verma, Crema-d: Crowd-sourced emotional multimodal actors dataset. IEEE Trans. Affect. Comput. 5(4), 377\u2013390 (2014)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"2817_CR9","unstructured":"K. Dupuis, & M. K. Pichora-Fuller, Toronto emotional speech set (tess)-younger talker_happy. (2010)"},{"issue":"3","key":"2817_CR10","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1016\/j.patcog.2010.09.020","volume":"44","author":"M El Ayadi","year":"2011","unstructured":"M. El Ayadi, M.S. Kamel, F. Karray, Survey on speech emotion recognition: Features, classification schemes, and databases. Pattern Recogn. 44(3), 572\u2013587 (2011)","journal-title":"Pattern Recogn."},{"key":"2817_CR11","doi-asserted-by":"publisher","first-page":"1007","DOI":"10.1007\/s10796-020-10012-9","volume":"23","author":"A Elena-Bucea","year":"2021","unstructured":"A. Elena-Bucea, F. Cruz-Jesus, T. Oliveira, P.S. Coelho, Assessing the role of age, education, gender and income on the digital divide: Evidence for the European Union. Inf. Syst. Front. 23, 1007\u20131021 (2021)","journal-title":"Inf. Syst. Front."},{"key":"2817_CR12","doi-asserted-by":"crossref","unstructured":"I. S. Engberg, A. V. Hansen, O. Andersen, & P. Dalsgaard, Design, recording and verification of a Danish emotional speech database. In Fifth European conference on speech communication and technology. (1997)","DOI":"10.21437\/Eurospeech.1997-482"},{"issue":"5","key":"2817_CR13","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1016\/j.jadohealth.2020.08.006","volume":"67","author":"G Gonzales","year":"2020","unstructured":"G. Gonzales, E.L. de Mola, K.A. Gavulic, T. McKay, C. Purcell, Mental health needs among lesbian, gay, bisexual, and transgender college students during the COVID-19 pandemic. J. Adolesc. Health. 67(5), 645\u2013648 (2020)","journal-title":"J. Adolesc. Health."},{"key":"2817_CR14","doi-asserted-by":"crossref","unstructured":"S. Goyal, V. V. Patage, & S. Tiwari, Gender and age group predictions from speech features using multi-layer perceptron model. In: 2020 IEEE 17th India Council International Conference (INDICON) pp. 1\u20136. IEEE. (2020)","DOI":"10.1109\/INDICON49873.2020.9342434"},{"key":"2817_CR15","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1016\/j.jpeds.2020.03.013","volume":"221","author":"WY Jiao","year":"2020","unstructured":"W.Y. Jiao, L.N. Wang, J. Liu, S.F. Fang, F.Y. Jiao, M. Pettoello-Mantovani, E. Somekh, Behavioural and emotional disorders in children during the COVID-19 epidemic. J. Pediatr. 221, 264\u2013266 (2020)","journal-title":"J. Pediatr."},{"key":"2817_CR16","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1007\/s10772-011-9125-1","volume":"15","author":"SG Koolagudi","year":"2012","unstructured":"S.G. Koolagudi, K.S. Rao, Emotion recognition from speech: A review. Int. J. Speech Technol. 15, 99\u2013117 (2012)","journal-title":"Int. J. Speech Technol."},{"key":"2817_CR17","doi-asserted-by":"crossref","unstructured":"S. G. Koolagudi, R. Reddy, & K. S. Rao, Emotion recognition from speech signal using epoch parameters. In: 2010 international conference on signal processing and communications (SPCOM) pp. 1\u20135. IEEE. (2010)","DOI":"10.1109\/SPCOM.2010.5560541"},{"key":"2817_CR18","unstructured":"S. R. Livingstone, K. Peck, & F. A. Russo, Ravdess: The ryerson audio-visual database of emotional speech and song. In: Annual meeting of the canadian society for brain, behaviour and cognitive science pp. 205\u2013211 (2012)"},{"issue":"5","key":"2817_CR19","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1176\/appi.ajp.2019.18111271","volume":"177","author":"LM McTeague","year":"2020","unstructured":"L.M. McTeague, B.M. Rosenberg, J.W. Lopez, D.M. Carreon, J. Huemer, Y. Jiang, C.F. Chick, S.B. Eickhoff, A. Etkin, Identification of common neural circuit disruptions in emotional processing across psychiatric disorders. Am. J. Psychiatry 177(5), 411\u2013421 (2020). https:\/\/doi.org\/10.1176\/appi.ajp.2019.18111271","journal-title":"Am. J. Psychiatry"},{"key":"2817_CR20","doi-asserted-by":"crossref","unstructured":"R. Pappagari, J. Villalba, P. \u017belasko, L. Moro-Velazquez, & N. Dehak, Copypaste: An augmentation method for speech emotion recognition. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 6324\u20136328. IEEE. (2021)","DOI":"10.1109\/ICASSP39728.2021.9415077"},{"key":"2817_CR21","doi-asserted-by":"crossref","unstructured":"D. S. Park, W. Chan, Y. Zhang, C. C. Chiu, B. Zoph, E. D. Cubuk, & Q. V. Le, Specaugment: A simple data augmentation method for automatic speech recognition. In: arXiv preprint arXiv:1904.08779 (2019)","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"2817_CR22","unstructured":"L. Schmid, A. Gerharz, A. Groll, & M. Pauly, Machine Learning for Multi-Output Regression In: When should a holistic multivariate approach be preferred over separate univariate ones?. arXiv preprint arXiv:2201.05340 (2022)"},{"key":"2817_CR23","unstructured":"M. Schroder, & R. Cowie, Issues in emotion-oriented computing-towards a shared understanding. In: Workshop on emotion and computing. Citeseer. (2006)"},{"key":"2817_CR24","doi-asserted-by":"crossref","unstructured":"X. Song, Z. Wu, Y. Huang, D. Su, & H. Meng, SpecSwap: A Simple Data Augmentation Method for End-to-End Speech Recognition. In: Interspeech pp. 581\u2013585 (2020)","DOI":"10.21437\/Interspeech.2020-2275"},{"issue":"2","key":"2817_CR25","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1109\/72.557662","volume":"8","author":"S Tamura","year":"1997","unstructured":"S. Tamura, M. Tateishi, Capabilities of a four-layered feedforward neural network: four layers versus three. IEEE Trans. Neural Networks 8(2), 251\u2013255 (1997). https:\/\/doi.org\/10.1109\/72.557662","journal-title":"IEEE Trans. Neural Networks"},{"issue":"17","key":"2817_CR26","doi-asserted-by":"publisher","first-page":"5892","DOI":"10.3390\/s21175892","volume":"21","author":"A Tursunov","year":"2021","unstructured":"A. Tursunov, J.Y. Mustaqeem, S.K. Choeh, Age and gender recognition using a convolutional neural network with a specially designed multi-attention module through speech spectrograms. Sensors 21(17), 5892 (2021). https:\/\/doi.org\/10.3390\/s21175892","journal-title":"Sensors"},{"issue":"9","key":"2817_CR27","doi-asserted-by":"publisher","first-page":"1162","DOI":"10.1016\/j.specom.2006.04.003","volume":"48","author":"D Ververidis","year":"2006","unstructured":"D. Ververidis, C. Kotropoulos, Emotional speech recognition: Resources, features, and methods. Speech Commun. 48(9), 1162\u20131181 (2006)","journal-title":"Speech Commun."},{"key":"2817_CR28","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1016\/j.future.2021.05.029","volume":"125","author":"S Wang","year":"2021","unstructured":"S. Wang, Z. Wu, G. He, S. Wang, H. Sun, F. Fan, Semi-supervised classification-aware cross-modal deep adversarial data augmentation. Futur. Gener. Comput. Syst. 125, 194\u2013205 (2021)","journal-title":"Futur. Gener. Comput. Syst."},{"key":"2817_CR29","doi-asserted-by":"crossref","unstructured":"T. M. Wani, T. S. Gunawan, H. Mansor, S. A. A. Qadri, A. Sophian, E. Ambikairajah, & E. Ihsanto, Multilanguage speech-based gender classification using time-frequency features and SVM classifier. In: Advances in robotics, automation and data analytics: selected papers from iCITES 2020 pp. 1\u201310 Springer (2021)","DOI":"10.1007\/978-3-030-70917-4_1"},{"key":"2817_CR30","doi-asserted-by":"publisher","unstructured":"S. R. Zaman et al. One source to detect them all: Gender, age, and emotion detection from voice. 2021 IEEE 45th Annual Computers, Software, and Applications Conference (COMPSAC), https:\/\/doi.org\/10.1109\/compsac51774.2021.00055 (2021)","DOI":"10.1109\/compsac51774.2021.00055"},{"key":"2817_CR31","doi-asserted-by":"publisher","first-page":"104486","DOI":"10.1016\/j.scs.2023.104486","volume":"92","author":"Q Zheng","year":"2023","unstructured":"Q. Zheng, X. Tian, Z. Yu, N. Jiang, A. Elhanashi, S. Saponara, R. Yu, Application of wavelet-packet transform driven deep learning method in PM2 5 concentration prediction: A case study of Qingdao. Chin. Sustain. Cities Soc. 92, 104486 (2023)","journal-title":"Chin. Sustain. Cities Soc."},{"key":"2817_CR32","doi-asserted-by":"publisher","first-page":"106082","DOI":"10.1016\/j.engappai.2023.106082","volume":"122","author":"Q Zheng","year":"2023","unstructured":"Q. Zheng, X. Tian, Z. Yu, H. Wang, A. Elhanashi, S. Saponara, DL-PR: Generalized automatic modulation classification method based on deep learning with priori regularization. Eng. Appl. Artif. Intell. 122, 106082 (2023)","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"13","key":"2817_CR33","doi-asserted-by":"publisher","first-page":"7723","DOI":"10.1007\/s00521-020-05514-1","volume":"33","author":"Q Zheng","year":"2021","unstructured":"Q. Zheng, P. Zhao, Y. Li, H. Wang, Y. Yang, Spectrum interference-based two-level data augmentation method in deep learning for automatic modulation classification. Neural Comput. Appl. 33(13), 7723\u20137745 (2021)","journal-title":"Neural Comput. Appl."},{"issue":"6","key":"2817_CR34","doi-asserted-by":"publisher","first-page":"1298","DOI":"10.1109\/LCOMM.2022.3145647","volume":"26","author":"Q Zheng","year":"2022","unstructured":"Q. Zheng, P. Zhao, H. Wang, A. Elhanashi, S. Saponara, Fine-grained modulation classification using multi-scale radio transformer with dual-channel representation. IEEE Commun. Lett. 26(6), 1298\u20131302 (2022)","journal-title":"IEEE Commun. Lett."},{"issue":"12","key":"2817_CR35","doi-asserted-by":"publisher","first-page":"7204","DOI":"10.1002\/int.22586","volume":"36","author":"Q Zheng","year":"2021","unstructured":"Q. Zheng, P. Zhao, D. Zhang, H. Wang, MR-DCAE: manifold regularization-based deep convolutional autoencoder for unauthorized broadcasting identification. Int. J. Intell. Syst. 36(12), 7204\u20137238 (2021)","journal-title":"Int. J. Intell. Syst."}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-024-02817-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00034-024-02817-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-024-02817-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T18:04:15Z","timestamp":1730570655000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00034-024-02817-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,8]]},"references-count":35,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["2817"],"URL":"https:\/\/doi.org\/10.1007\/s00034-024-02817-9","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"type":"print","value":"0278-081X"},{"type":"electronic","value":"1531-5878"}],"subject":[],"published":{"date-parts":[[2024,8,8]]},"assertion":[{"value":"5 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 August 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 August 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 August 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors of this paper do not have any conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}