{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T04:31:30Z","timestamp":1782361890119,"version":"3.54.5"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T00:00:00Z","timestamp":1634515200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T00:00:00Z","timestamp":1634515200000},"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":[[2022,12]]},"DOI":"10.1007\/s10772-021-09900-5","type":"journal-article","created":{"date-parts":[[2021,10,19]],"date-time":"2021-10-19T01:15:52Z","timestamp":1634606152000},"page":"817-830","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Construction of complex environment speech signal communication system based on 5G and AI driven feature extraction techniques"],"prefix":"10.1007","volume":"25","author":[{"given":"Yi","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"ErLi","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"YongHao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yali","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,10,18]]},"reference":[{"issue":"12","key":"9900_CR1","doi-asserted-by":"publisher","first-page":"2301","DOI":"10.1109\/TASLP.2016.2604566","volume":"24","author":"M Cernak","year":"2016","unstructured":"Cernak, M., Lazaridis, A., Asaei, A., et al. (2016). Composition of deep and spiking neural networks for very low bit rate speech coding[J]. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 24(12), 2301\u20132312.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"issue":"6","key":"9900_CR2","doi-asserted-by":"publisher","first-page":"4705","DOI":"10.1121\/1.4986931","volume":"141","author":"J Chen","year":"2017","unstructured":"Chen, J., & Wang, D. L. (2017). Long short-term memory for speaker generalization in supervised speech separation[J]. The Journal of the Acoustical Society of America, 141(6), 4705\u20134714.","journal-title":"The Journal of the Acoustical Society of America"},{"key":"9900_CR3","doi-asserted-by":"crossref","unstructured":"Erdogan H, Hershey J R, Watanabe S, et al. Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks[C]. 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, Brisbane, QLD, Australia, 2015, 4: 708\u2013712.","DOI":"10.1109\/ICASSP.2015.7178061"},{"issue":"4","key":"9900_CR4","first-page":"13","volume":"47","author":"W Hao","year":"2019","unstructured":"Hao, W., Yingxi, L., Bin, X., et al. (2019). Speech enhancement method based on convolution gated recurrent neural network [J]. Journal of Huazhong University of Science and Technology, 47(4), 13\u201318.","journal-title":"Journal of Huazhong University of Science and Technology"},{"issue":"12","key":"9900_CR5","doi-asserted-by":"publisher","first-page":"2136","DOI":"10.1109\/TASLP.2015.2468583","volume":"23","author":"PS Huang","year":"2015","unstructured":"Huang, P. S., Kim, M., Hasegawa-Johnson, M., et al. (2015). Joint optimization of masks and deep recurrent neural networks for monaural source separation[J]. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 23(12), 2136\u20132147.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"issue":"1","key":"9900_CR6","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1007\/s11771-016-3057-5","volume":"23","author":"SK Kim","year":"2016","unstructured":"Kim, S. K., Park, Y. J., & Lee, S. (2016). Voice activity detection based on deep belief networks using likelihood ratio[J]. Journal of Central South University, 23(1), 145\u2013149.","journal-title":"Journal of Central South University"},{"issue":"4","key":"9900_CR7","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1049\/iet-spr.2015.0375","volume":"10","author":"Y Li","year":"2016","unstructured":"Li, Y., & Kang, S. (2016). Artificial bandwidth extension using deep neural network-based spectral envelope estimation and enhanced excitation estimation[J]. IET Signal Processing, 10(4), 422\u2013427.","journal-title":"IET Signal Processing"},{"issue":"2","key":"9900_CR8","doi-asserted-by":"publisher","first-page":"964","DOI":"10.1109\/TEC.2018.2872118","volume":"34","author":"Z Li","year":"2018","unstructured":"Li, Z., Cadet, C., & Outbib, R. (2018). Diagnosis for PEMFC based on magnetic measurements and data-driven approach. IEEE Transactions on Energy Conversion, 34(2), 964\u2013972.","journal-title":"IEEE Transactions on Energy Conversion"},{"issue":"3","key":"9900_CR9","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1109\/MSP.2014.2359987","volume":"32","author":"ZH Ling","year":"2015","unstructured":"Ling, Z. H., Kang, S. Y., Zen, H., et al. (2015). Deep learning for acoustic modeling in parametric speech generation: a systematic review of existing techniques and future trends[J]. IEEE Signal Processing Magazine, 32(3), 35\u201352.","journal-title":"IEEE Signal Processing Magazine"},{"key":"9900_CR10","doi-asserted-by":"crossref","unstructured":"Liu M, Wang Y, Wang J, et al. Speech Enhancement Method Based On LSTM Neural Network for Speech Recognition[C]. 2018 14th IEEE International Conference on Signal Processing (ICSP). IEEE, Beijing, China, 2018, 8: 245\u2013249.","DOI":"10.1109\/ICSP.2018.8652331"},{"key":"9900_CR11","doi-asserted-by":"publisher","first-page":"e109980","DOI":"10.1016\/j.rser.2020.109980","volume":"131","author":"XJ Luo","year":"2020","unstructured":"Luo, X. J., Oyedele, Lukumon O., Ajayi, Anuoluwapo O., Akinade, Olugbenga O., Owolabi, Hakeem A., & Ahmed, Ashraf. (2020). Feature extraction and genetic algorithm enhanced adaptive deep neural network for energy consumption prediction in buildings. Renewable and Sustainable Energy Reviews, 131, e109980.","journal-title":"Renewable and Sustainable Energy Reviews"},{"issue":"9","key":"9900_CR12","doi-asserted-by":"publisher","first-page":"7171","DOI":"10.1109\/TIE.2017.2688970","volume":"64","author":"Y Ma","year":"2017","unstructured":"Ma, Y., & Huang, B. (2017). Bayesian learning for dynamic feature extraction with application in soft sensing. IEEE Transactions on Industrial Electronics, 64(9), 7171\u20137180.","journal-title":"IEEE Transactions on Industrial Electronics"},{"key":"9900_CR13","doi-asserted-by":"crossref","unstructured":"Michelsanti D, Tan Z H. Conditional generative adversarial networks for speech enhancement and noise-robust speaker verification[J]. arXiv preprint arXiv: 1709.01703, 2017.","DOI":"10.21437\/Interspeech.2017-1620"},{"key":"9900_CR14","unstructured":"Novotny O, Plchot O, Glembek O, et al. Analysis of DNN Speech Signal Enhancement for Robust Speaker Recognition[J]. arXiv preprint arXiv: 1811.07629, 2018."},{"key":"9900_CR15","doi-asserted-by":"crossref","unstructured":"Park S R, Lee J. A fully convolutional neural network for speech enhancement[J]. arXiv preprint arXiv: 1609.07132, 2016.","DOI":"10.21437\/Interspeech.2017-1465"},{"key":"9900_CR16","volume-title":"Research on speech enhancement based on multi-objective learning and fusion of deep neural network [D]","author":"W Qing","year":"2018","unstructured":"Qing, W. (2018). Research on speech enhancement based on multi-objective learning and fusion of deep neural network [D]. University of science and technology of China."},{"key":"9900_CR17","volume-title":"Speech signal processing: C + + version [M]","author":"L Ruiyu","year":"2018","unstructured":"Ruiyu, L., Li, Z., Qingyun, W., et al. (2018). Speech signal processing: C + + version [M]. China Machine Press."},{"issue":"5","key":"9900_CR18","doi-asserted-by":"publisher","first-page":"5007","DOI":"10.1109\/TSG.2018.2873001","volume":"10","author":"M Sun","year":"2018","unstructured":"Sun, M., Konstantelos, I., & Strbac, G. (2018). A deep learning-based feature extraction framework for system security assessment. IEEE Transactions on Smart Grid, 10(5), 5007\u20135020.","journal-title":"IEEE Transactions on Smart Grid"},{"key":"9900_CR19","unstructured":"Wai C.Chu.Speech Coding Algorithms: Foundation and Evolution of Standardized Coders[M]. Hoboken and New Jersey:A John Wiley & Sons,Inc,2003:1\u201360."},{"key":"9900_CR20","doi-asserted-by":"publisher","first-page":"80122","DOI":"10.1109\/ACCESS.2019.2923583","volume":"7","author":"J Wan","year":"2019","unstructured":"Wan, J., Zheng, P., Si, H., Xiong, N. N., Zhang, W., & Vasilakos, A. V. (2019). An artificial intelligence driven multi-feature extraction scheme for big data detection. IEEE Access, 7, 80122\u201380132.","journal-title":"IEEE Access"},{"key":"9900_CR21","doi-asserted-by":"crossref","unstructured":"Wang Y, Zhao S, Liu W, et al. Speech Bandwidth Expansion Based on Deep Neural Networks[C]\/\/Interspeech. 2015: 2593\u20132597.","DOI":"10.21437\/Interspeech.2015-558"},{"key":"9900_CR22","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1007\/978-3-319-22482-4_11","volume":"8","author":"F Weninger","year":"2015","unstructured":"Weninger, F., Erdogan, H., Watanabe, S., et al. (2015). Speech enhancement with LSTM recurrent neural networks and its application to noise-robust ASR[C]. International Conference on Latent Variable Analysis and Signal Separation, Liberec, Czech Republic, 8, 91\u201399.","journal-title":"International Conference on Latent Variable Analysis and Signal Separation, Liberec, Czech Republic"},{"key":"9900_CR23","unstructured":"Li Xiaodong. Research and implementation of an improved speech codec algorithm [D]. University of Defense Science and technology, 2011:3\u201310."},{"key":"9900_CR24","unstructured":"Xu Y, Du J, Huang Z, et al. Multi-objective learning and mask-based post-processing for deep neural network based speech enhancement[J]. arXiv preprint arXiv: 1703.07172, 2017."},{"issue":"1","key":"9900_CR25","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1109\/TASLP.2014.2364452","volume":"23","author":"Y Xu","year":"2015","unstructured":"Xu, Y., Du, J., Dai, L. R., et al. (2015). A regression approach to speech enhancement based on deep neural networks[J]. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 23(1), 7\u201319.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"9900_CR26","unstructured":"Feng Xudong. Research and implementation of low bit rate error resilient speech coding algorithm [D]. Xi'an University of Electronic Science and technology, 2013:2\u201315."},{"key":"9900_CR27","unstructured":"Jiang Xuehua. Digital speech compression system based on arm [D]. Hunan University. 2007:2\u20138."},{"issue":"1","key":"9900_CR28","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1631\/FITEE.1601883","volume":"18","author":"Y-T Zhuang","year":"2017","unstructured":"Zhuang, Y.-T., Fei, Wu., Chen, C., & Pan, Y.-h. (2017). Challenges and opportunities: from big data to knowledge in AI 2.0. Frontiers of Information Technology & Electronic Engineering, 18(1), 3\u201314.","journal-title":"Frontiers of Information Technology & Electronic Engineering"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09900-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-021-09900-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09900-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,11]],"date-time":"2023-11-11T10:08:05Z","timestamp":1699697285000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-021-09900-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,18]]},"references-count":28,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["9900"],"URL":"https:\/\/doi.org\/10.1007\/s10772-021-09900-5","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,18]]},"assertion":[{"value":"3 February 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 September 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 October 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}