{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T11:17:27Z","timestamp":1784114247419,"version":"3.55.0"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"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":["Int J Speech Technol"],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1007\/s10772-024-10107-7","type":"journal-article","created":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T11:04:02Z","timestamp":1717067042000},"page":"319-327","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Feature fusion: research on emotion recognition in English speech"],"prefix":"10.1007","volume":"27","author":[{"given":"Yongyan","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,5,30]]},"reference":[{"key":"10107_CR1","doi-asserted-by":"publisher","first-page":"119633","DOI":"10.1016\/j.eswa.2023.119633","volume":"218","author":"MR Ahmed","year":"2023","unstructured":"Ahmed, M. R., Islam, S., Islam, A. M., & Shatabda, S. (2023). An ensemble 1D-CNN-LSTM-GRU model with data augmentation for speech emotion recognition. Expert Systems with Applications, 218, 119633.","journal-title":"Expert Systems with Applications"},{"issue":"3","key":"10107_CR2","first-page":"89","volume":"98","author":"S Ayadi","year":"2022","unstructured":"Ayadi, S., & Lachiri, Z. (2022). Visual emotion sensing using convolutional neural network. Przeglad Elektrotechniczny, 98(3), 89\u201392.","journal-title":"Przeglad Elektrotechniczny"},{"issue":"7","key":"10107_CR3","doi-asserted-by":"publisher","first-page":"9693","DOI":"10.1007\/s11042-021-11839-3","volume":"82","author":"S Chattopadhyay","year":"2023","unstructured":"Chattopadhyay, S., Dey, A., Singh, P. K., Ahmadian, A., & Sarkar, R. (2023). A feature selection model for speech emotion recognition using clustering-based population generation with hybrid of equilibrium optimizer and atom search optimization algorithm. Multimedia Tools and Applications, 82(7), 9693\u20139726.","journal-title":"Multimedia Tools and Applications"},{"issue":"3","key":"10107_CR4","first-page":"1","volume":"598","author":"Y Chen","year":"2021","unstructured":"Chen, Y., Liu, G., Huang, X., Chen, K., Hou, J., & Zhou, J. (2021). Development of a surrogate method of groundwater modeling using gated recurrent unit to improve the efficiency of parameter auto-calibration and global sensitivity analysis. Journal of Hydrology, 598(3), 1\u201316.","journal-title":"Journal of Hydrology"},{"key":"10107_CR5","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1016\/j.specom.2021.11.005","volume":"136","author":"L Guo","year":"2022","unstructured":"Guo, L., Wang, L., Dang, J., Chng, E. S., & Nakagawa, S. (2022). Learning affective representations based on magnitude and dynamic relative phase information for speech emotion recognition - ScienceDirect. Speech Communication, 136, 118\u2013127.","journal-title":"Speech Communication"},{"issue":"2","key":"10107_CR6","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1111\/acps.13388","volume":"145","author":"L Hansen","year":"2021","unstructured":"Hansen, L., Zhang, Y. P., Wolf, D., Sechidis, K., Ladegaard, N., & Fusaroli, R. (2021). A generalizable speech emotion recognition model reveals depression and remission. Acta Psychiatrica Scandinavica, 145(2), 186\u2013199.","journal-title":"Acta Psychiatrica Scandinavica"},{"issue":"8","key":"10107_CR7","doi-asserted-by":"publisher","first-page":"1391","DOI":"10.1587\/transinf.2021EDL8002","volume":"E104.D","author":"D Hu","year":"2021","unstructured":"Hu, D., Chen, C., Zhang, P., Li, J., Yan, Y., & Zhao, Q. (2021). A two-stage attention based modality fusion framework for multi-modal speech emotion recognition. IEICE Transactions on Information and Systems, E104.D(8), 1391\u20131394.","journal-title":"IEICE Transactions on Information and Systems"},{"key":"10107_CR8","unstructured":"Hu, Z., Wang, L., Luo, Y., Xia, Y., & Xiao, H. (2022). Speech emotion recognition model based on attention CNN Bi-GRU fusing visual information. Engineering Letters, 30(2)."},{"key":"10107_CR9","doi-asserted-by":"publisher","first-page":"188","DOI":"10.14738\/assrj.84.9839","volume":"8","author":"H Hyder","year":"2021","unstructured":"Hyder, H. (2021). The pedagogy of English language teaching using CBSE methodologies for schools. Advances in Social Sciences Research Journal, 8, 188\u2013193.","journal-title":"Advances in Social Sciences Research Journal"},{"issue":"4","key":"10107_CR10","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1002\/ima.22337","volume":"29","author":"Z Li","year":"2019","unstructured":"Li, Z., Wang, S. H., Fan, R. R., Cao, G., Zhang, Y. D., & Guo, T. (2019). Teeth category classification via seven-layer deep convolutional neural network with max pooling and global average pooling. International Journal of Imaging Systems and Technology, 29(4), 577\u2013583.","journal-title":"International Journal of Imaging Systems and Technology"},{"issue":"May 11","key":"10107_CR11","first-page":"1","volume":"243","author":"LY Liu","year":"2022","unstructured":"Liu, L. Y., Liu, W. Z., Zhou, J., Deng, H. Y., & Feng, L. (2022). ATDA: Attentional temporal dynamic activation for speech emotion recognition. Knowledge-based Systems, 243(May 11), 1\u201311.","journal-title":"Knowledge-based Systems"},{"key":"10107_CR12","doi-asserted-by":"crossref","unstructured":"Nfissi, A., Bouachir, W., Bouguila, N., & Mishara, B. L. (2022). CNN-n-GRU: End-to-end speech emotion recognition from raw waveform signal using CNNs and gated recurrent unit networks. In 21st IEEE international conference on machine learning and applications (ICMLA), (pp. 699\u2013702).","DOI":"10.1109\/ICMLA55696.2022.00116"},{"key":"10107_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.apenergy.2022.118801","volume":"313","author":"D Niu","year":"2022","unstructured":"Niu, D., Yu, M., Sun, L., Gao, T., & Wang, K. (2022). Short-term multi-energy load forecasting for integrated energy systems based on CNN-BiGRU optimized by attention mechanism. Applied Energy, 313, 1\u201317.","journal-title":"Applied Energy"},{"issue":"1","key":"10107_CR14","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1002\/int.22291","volume":"36","author":"ENN Ocquaye","year":"2021","unstructured":"Ocquaye, E. N. N., Mao, Q., Xue, Y., & Song, H. (2021). Cross lingual speech emotion recognition via triple attentive asymmetric convolutional neural network. International Journal of Intelligent Systems, 36(1), 53\u201371.","journal-title":"International Journal of Intelligent Systems"},{"issue":"2","key":"10107_CR15","first-page":"1","volume":"71","author":"SK Pandey","year":"2022","unstructured":"Pandey, S. K., Shekhawat, H. S., & Prasanna, S. R. M. (2022). Attention gated tensor neural network architectures for speech emotion recognition. Biomedical Signal Processing and Control, 71(2), 1\u201316.","journal-title":"Biomedical Signal Processing and Control"},{"key":"10107_CR16","doi-asserted-by":"crossref","unstructured":"Peng, Z., Zhu, Z., Unoki, M., Dang, J., Akagi, M. (2018). Auditory-inspired end-to-end speech emotion recognition using 3D convolutional recurrent neural networks based on spectral-temporal representation. In 2018 IEEE international conference on, multimedia, & expo. (ICME) (pp. 1\u20136), San Diego, CA, USA.","DOI":"10.1109\/ICME.2018.8486564"},{"issue":"19","key":"10107_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1002\/cpe.7038","volume":"34","author":"A Ponmalar","year":"2022","unstructured":"Ponmalar, A., & Dhanakoti, V. (2022). Hybrid whale tabu algorithm optimized convolutional neural network architecture for intrusion detection in big data. Concurrency and Computation: Practice and Experience, 34(19), 1\u201315.","journal-title":"Concurrency and Computation: Practice and Experience"},{"issue":"2","key":"10107_CR18","first-page":"281","volume":"48","author":"D Qiao","year":"2022","unstructured":"Qiao, D., Chen, Z. J., Deng, L., & Tu, C. L. (2022). Method for Chinese speech emotion recognition based on improved speech-processing convolutional neural network. Computer Engineering, 48(2), 281\u2013290.","journal-title":"Computer Engineering"},{"issue":"10","key":"10107_CR19","doi-asserted-by":"publisher","first-page":"1265","DOI":"10.1049\/iet-its.2019.0732","volume":"14","author":"AF Requardt","year":"2020","unstructured":"Requardt, A. F., Ihme, K., Wilbrink, M., & Wendemuth, A. (2020). Towards affect-aware vehicles for increasing safety and comfort: Recognising driver emotions from audio recordings in a realistic driving study. IET Intelligent Transport Systems, 14(10), 1265\u20131277.","journal-title":"IET Intelligent Transport Systems"},{"key":"10107_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2020\/4851909","volume":"2020(2)","author":"M Tan","year":"2020","unstructured":"Tan, M., Wang, C., Yuan, H., Bai, J., & An, L. (2020). FDA-MIMO Beampattern synthesis with Hamming window weighted linear frequency increments. International Journal of Aerospace Engineering, 2020(2), 1\u20138.","journal-title":"International Journal of Aerospace Engineering"},{"key":"10107_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.apacoust.2022.108637","volume":"190","author":"D Tanko","year":"2022","unstructured":"Tanko, D., Dogan, S., Demir, F. B., Baygin, M., Sahin, S. E., & Tuncer, T. (2022). Shoelace pattern-based speech emotion recognition of the lecturers in distance education: ShoePat23. Applied Acoustics, 190, 1\u20139.","journal-title":"Applied Acoustics"},{"key":"10107_CR22","doi-asserted-by":"crossref","unstructured":"Wibawa, I. D. G. Y. A., & Darmawan, I. D. M. B. A. (2021). Implementation of audio recognition using mel frequency cepstrum coefficient and dynamic time warping in wirama praharsini. Journal of Physics: Conference Series, 1722, 1\u20138.","DOI":"10.1088\/1742-6596\/1722\/1\/012014"},{"key":"10107_CR24","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Zheng, Y., Zhang, Z., Wang, H., Zhao, Y., & Li, C. (2018). Exploring spatio-temporal representations by integrating attention-based bidirectional-LSTM-RNNs and FCNs for speech emotion recognition. In Annual conference of the international speech communication association, (pp. 272\u2013276).","DOI":"10.21437\/Interspeech.2018-1477"},{"key":"10107_CR23","doi-asserted-by":"publisher","first-page":"97515","DOI":"10.1109\/ACCESS.2019.2928625","volume":"7","author":"Z Zhao","year":"2019","unstructured":"Zhao, Z., Bao, Z., Zhao, Y., Zhang, Z., Cummins, N., Ren, Z., & Schuller, B. (2019). Exploring deep spectrum representations via attention-based recurrent and convolutional neural networks for Speech emotion recognition. IEEE Access: Practical Innovations, Open Solutions, 7, 97515\u201397525.","journal-title":"IEEE Access: Practical Innovations, Open Solutions"},{"key":"10107_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cageo.2021.104862","volume":"156","author":"M Zhu","year":"2021","unstructured":"Zhu, M., Cheng, J., & Zhang, Z. (2021). Quality control of microseismic P-phase arrival picks in coal mine based on machine learning. Computers & Geosciences, 156, 1\u201312.","journal-title":"Computers & Geosciences"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-024-10107-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-024-10107-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-024-10107-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T16:06:28Z","timestamp":1721664388000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-024-10107-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":25,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["10107"],"URL":"https:\/\/doi.org\/10.1007\/s10772-024-10107-7","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,30]]},"assertion":[{"value":"15 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 May 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 May 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}