{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T03:44:30Z","timestamp":1786160670199,"version":"build-2736575974"},"reference-count":31,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100010029","name":"Taishan Scholar Foundation of Shandong Province","doi-asserted-by":"publisher","award":["tstp20250506"],"award-info":[{"award-number":["tstp20250506"]}],"id":[{"id":"10.13039\/501100010029","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013076","name":"National Major Science and Technology Projects of China","doi-asserted-by":"publisher","award":["2022ZD0119501"],"award-info":[{"award-number":["2022ZD0119501"]}],"id":[{"id":"10.13039\/501100013076","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Soft Computing"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.asoc.2026.116136","type":"journal-article","created":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T15:14:19Z","timestamp":1785942859000},"page":"116136","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["Cross-lingual speech emotion recognition via multi-ethnic wavelet-based data augmentation and feature decoupling"],"prefix":"10.1016","volume":"203","author":[{"given":"Faming","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9224-6115","authenticated-orcid":false,"given":"Yi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6162-1922","authenticated-orcid":false,"given":"Zedong","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"YunXia","family":"Bao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.asoc.2026.116136_bib0005","first-page":"37","article-title":"Review on speech emotion recognition","volume":"25","author":"Han","year":"2014","journal-title":"Ruan Jian Xue Bao\/J. Softw."},{"key":"10.1016\/j.asoc.2026.116136_bib0010","first-page":"645","article-title":"Prototype of educational affective arousal evaluation system based on facial and speech emotion recognition","volume":"9","author":"Liu","year":"2019","journal-title":"Int. J. Inf. Educ. Technol."},{"key":"10.1016\/j.asoc.2026.116136_bib0015","doi-asserted-by":"crossref","DOI":"10.1155\/2022\/7463091","article-title":"Human-computer interaction with detection of speaker emotions using convolution neural networks","volume":"2022","author":"Alnuaim","year":"2022","journal-title":"Comput. Intell. Neurosci."},{"key":"10.1016\/j.asoc.2026.116136_bib0020","doi-asserted-by":"crossref","first-page":"5571","DOI":"10.1007\/s11042-017-5292-7","article-title":"Deep features-based speech emotion recognition for smart affective services","volume":"78","author":"Badshah","year":"2019","journal-title":"Multimed. Tools Appl."},{"key":"10.1016\/j.asoc.2026.116136_bib0025","doi-asserted-by":"crossref","first-page":"2830","DOI":"10.1109\/TITS.2021.3119921","article-title":"Speech emotion recognition enhanced traffic efficiency solution for autonomous vehicles in a 5G-enabled space-air-ground integrated intelligent transportation system","volume":"23","author":"Tan","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.asoc.2026.116136_bib0030","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","article-title":"IEMOCAP: interactive emotional dyadic motion capture database","volume":"42","author":"Busso","year":"2008","journal-title":"Lang. Resour. Eval."},{"key":"10.1016\/j.asoc.2026.116136_bib0035","first-page":"1","article-title":"The generation of affect in synthesized speech","volume":"8","author":"Cahn","year":"1990","journal-title":"J. Am. Voice Input\/Output Soc."},{"key":"10.1016\/j.asoc.2026.116136_bib0040","series-title":"Proceedings of the 1999 IEEE International Conference on Multimedia Computing and Systems (ICMCS)","first-page":"840","article-title":"Emotion recognition and synthesis system on speech","author":"Moriyama","year":"1999"},{"key":"10.1016\/j.asoc.2026.116136_bib0045","author":"Wen"},{"key":"10.1016\/j.asoc.2026.116136_bib0050","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1007\/s10462-024-11065-x","article-title":"Real-time speech emotion recognition using deep learning and data augmentation","volume":"58","author":"Barhoumi","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.asoc.2026.116136_bib0055","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1007\/s11760-024-03773-2","article-title":"Speech emotion recognition based on multimodal and multiscale feature fusion","volume":"19","author":"Hu","year":"2024","journal-title":"Signal Image Video Process."},{"key":"10.1016\/j.asoc.2026.116136_bib0060","doi-asserted-by":"crossref","first-page":"4015","DOI":"10.3390\/electronics14204015","article-title":"Facial and speech-based emotion recognition using sequential pattern mining","volume":"14","author":"Song","year":"2025","journal-title":"Electronics"},{"key":"10.1016\/j.asoc.2026.116136_bib0065","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2025.113915","article-title":"Improving speech emotion recognition using gated cross-modal attention and multimodal homogeneous feature discrepancy learning","volume":"185","author":"Li","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.asoc.2026.116136_bib0070","doi-asserted-by":"crossref","DOI":"10.1016\/j.apacoust.2024.110169","article-title":"TRNet: two-level refinement network leveraging speech enhancement for noise robust speech emotion recognition","volume":"225","author":"Chen","year":"2024","journal-title":"Appl. Acoust."},{"key":"10.1016\/j.asoc.2026.116136_bib0075","doi-asserted-by":"crossref","first-page":"111","DOI":"10.3390\/technologies12070111","article-title":"Optimizing speech emotion recognition with machine learning based advanced audio cue analysis","volume":"12","author":"Pallewela","year":"2024","journal-title":"Technologies"},{"key":"10.1016\/j.asoc.2026.116136_bib0080","article-title":"Speech emotion recognition using multi-scale global\u2013local representation learning with feature pyramid network","volume":"14","author":"Wang","year":"2024","journal-title":"Appl. Sci."},{"key":"10.1016\/j.asoc.2026.116136_bib0085","series-title":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"Hierarchical network with decoupled knowledge distillation for speech emotion recognition","author":"Zhao","year":"2023"},{"key":"10.1016\/j.asoc.2026.116136_bib0090","series-title":"2024 IEEE Spoken Language Technology Workshop (SLT)","first-page":"698","article-title":"Disentangling the prosody and semantic information with pre-trained model for in-context learning based zero-shot voice conversion","author":"Chen","year":"2024"},{"key":"10.1016\/j.asoc.2026.116136_bib0095","series-title":"Advances in Neural Information Processing Systems","first-page":"737","article-title":"Signature verification using a \u201cSiamese\u201d time delay neural network","volume":"vol. 6","author":"Bromley","year":"1993"},{"key":"10.1016\/j.asoc.2026.116136_bib0100","series-title":"Proceedings of the 30th ACM International Conference on Multimedia","first-page":"1642","article-title":"Disentangled representation learning for multimodal emotion recognition","author":"Yang","year":"2022"},{"key":"10.1016\/j.asoc.2026.116136_bib0105","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0196391","article-title":"The Ryerson audio-visual database of emotional speech and song (RAVDESS): a dynamic, multimodal set of facial and vocal expressions in North American english","volume":"13","author":"Livingstone","year":"2018","journal-title":"PLoS One"},{"key":"10.1016\/j.asoc.2026.116136_bib0110","first-page":"17","article-title":"Fault diagnosis of rolling bearings based on wavelet packet analysis","volume":"28","author":"Zhang","year":"2007","journal-title":"J. Jiangxi Univ. Sci. Technol."},{"key":"10.1016\/j.asoc.2026.116136_bib0115","series-title":"Theoretical Research and Application of Empirical Mode Decomposition Method","author":"Fu","year":"2013"},{"key":"10.1016\/j.asoc.2026.116136_bib0120","first-page":"38","article-title":"Research on GA-SVM fault diagnosis method for rolling bearings based on wavelet packet and singular value decomposition","author":"Qin","year":"2016","journal-title":"Mech. Des. Manuf."},{"key":"10.1016\/j.asoc.2026.116136_bib0125","first-page":"1037","article-title":"Selection of wavelet basis functions in the fitting process of seismic ground motion response spectrum","volume":"37","author":"Bai","year":"2015","journal-title":"Acta Seismol. Sin."},{"key":"10.1016\/j.asoc.2026.116136_bib0130","series-title":"Interspeech 2005","first-page":"1517","article-title":"A database of German emotional speech","author":"Burkhardt","year":"2005"},{"key":"10.1016\/j.asoc.2026.116136_bib0135","series-title":"Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC\u201914)","doi-asserted-by":"crossref","first-page":"3501","DOI":"10.63317\/4i4sxkp59t9f","article-title":"EMOVO corpus: an Italian emotional speech database","author":"Costantini","year":"2014"},{"key":"10.1016\/j.asoc.2026.116136_bib0140","series-title":"Surrey Audio-Visual Expressed Emotion (SAVEE) Database","author":"Jackson","year":"2014"},{"key":"10.1016\/j.asoc.2026.116136_bib0145","series-title":"Proceedings of the 4th ACM International Conference on Multimedia in Asia","first-page":"1","article-title":"Speaker VGG CCT: cross-corpus speech emotion recognition with speaker embedding and vision transformers","author":"Arezzo","year":"2022"},{"key":"10.1016\/j.asoc.2026.116136_bib0150","author":"Tang"},{"key":"10.1016\/j.asoc.2026.116136_bib0155","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2024.108841","article-title":"Cross-corpus speech emotion recognition with transformers: leveraging handcrafted features and data augmentation","volume":"179","author":"Alroobaea","year":"2024","journal-title":"Comput. Biol. Med."}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S156849462601584X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S156849462601584X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T03:41:36Z","timestamp":1786160496000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S156849462601584X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":31,"alternative-id":["S156849462601584X"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2026.116136","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Cross-lingual speech emotion recognition via multi-ethnic wavelet-based data augmentation and feature decoupling","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2026.116136","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"116136"}}