{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:03:12Z","timestamp":1775228592050,"version":"3.50.1"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2016,2,22]],"date-time":"2016-02-22T00:00:00Z","timestamp":1456099200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Nature Science Foundation of China","doi-asserted-by":"crossref","award":["61272211"],"award-info":[{"award-number":["61272211"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the Six Talent Peaks Foundation of Jiangsu Province","award":["DZXX-027"],"award-info":[{"award-number":["DZXX-027"]}]},{"name":"the general Financial Grant from the China Postdoctoral Science Foundation","award":["2015M570413"],"award-info":[{"award-number":["2015M570413"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2017,3]]},"DOI":"10.1007\/s11042-016-3354-x","type":"journal-article","created":{"date-parts":[[2016,2,22]],"date-time":"2016-02-22T02:44:06Z","timestamp":1456109046000},"page":"6785-6799","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":54,"title":["Unsupervised domain adaptation for speech emotion recognition using PCANet"],"prefix":"10.1007","volume":"76","author":[{"given":"Zhengwei","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wentao","family":"Xue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qirong","family":"Mao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongzhao","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,2,22]]},"reference":[{"key":"3354_CR1","doi-asserted-by":"crossref","unstructured":"Abdel-Hamid O, Mohamed A, Jiang H, Penn G (2012) Applying convolutional neural networks concepts to hybrid nn-hmm model for speech recognition. In: 2012 IEEE international conference on Acoustics, speech and signal processing (ICASSP), pp 4277\u20134280","DOI":"10.1109\/ICASSP.2012.6288864"},{"key":"3354_CR2","unstructured":"Bengio Y (2012) Deep learning of representations for unsupervised and transfer learning. In: Unsupervised and transfer learning challenges in machine learning, vol 7, p 19"},{"key":"3354_CR3","doi-asserted-by":"crossref","unstructured":"Burkhardt F, Paeschke A, Rolfes M, Sendlmeier W, Weiss B (2005) A database of german emotional speech, vol 5","DOI":"10.21437\/Interspeech.2005-446"},{"key":"3354_CR4","unstructured":"Chan TH, Jia K, Gao S, Lu J, Zeng Z, Pcanet MY (2014) A simple deep learning baseline for image classification? arXiv preprint arXiv: 1404.3606"},{"key":"3354_CR5","unstructured":"Chopra S, Balakrishnan S, Dlid GR (2013) Deep learning for domain adaptation by interpolating between domains. ICML workshop on challenges in representation learning 2:5"},{"issue":"1","key":"3354_CR6","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","volume":"20","author":"GE Dahl","year":"2012","unstructured":"Dahl GE, Yu D, Deng L, Acero A (2012) Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Trans Audio Speech Lang Process 20(1):30\u2013 42","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"3354_CR7","doi-asserted-by":"crossref","unstructured":"Daum\u00e9 I IIH, Marcu D (2006) Domain adaptation for statistical classifiers. J Artif Intell Res:101\u2013 126","DOI":"10.1613\/jair.1872"},{"key":"3354_CR8","doi-asserted-by":"crossref","unstructured":"Deng J, Xia R, Zhang Z, Liu Y, Schuller B (2014) Introducing shared-hidden-layer autoencoders for transfer learning and their application in acoustic emotion recognition. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 4818\u20134822","DOI":"10.1109\/ICASSP.2014.6854517"},{"key":"3354_CR9","doi-asserted-by":"crossref","unstructured":"Deng J, Zhang Z, Marchi E, Schuller B (2013) Sparse autoencoder-based feature transfer learning for speech emotion recognition. In: 2013 Humaine Association Conference on Affective computing and intelligent interaction (ACII), pp 511\u2013516","DOI":"10.1109\/ACII.2013.90"},{"issue":"9","key":"3354_CR10","doi-asserted-by":"crossref","first-page":"1068","DOI":"10.1109\/LSP.2014.2324759","volume":"21","author":"J Deng","year":"2014","unstructured":"Deng J, Zhang Z, Eyben F, Schuller B (2014) Autoencoder-based unsupervised domain adaptation for speech emotion recognition. IEEE Signal Process Lett 21(9):1068\u20131072","journal-title":"IEEE Signal Process Lett"},{"key":"3354_CR11","doi-asserted-by":"crossref","unstructured":"Eyben F, Wollmer M, Schuller B (2009) Openear-introducing the munich open-source emotion and affect recognition toolkit, pp 1\u20136","DOI":"10.1109\/ACII.2009.5349350"},{"key":"3354_CR12","doi-asserted-by":"crossref","unstructured":"Fernando B, Habrard A, Sebban M, Tuytelaars T (2013) Unsupervised visual domain adaptation using subspace alignment, pp 2960\u20132967","DOI":"10.1109\/ICCV.2013.368"},{"key":"3354_CR13","unstructured":"Glorot X, Bordes A, Bengio Y (2011) Domain adaptation for large-scale sentiment classification: A deep learning approach. In: Inproceedings of the 28th International Conference on Machine Learning, pp 513\u2013520"},{"issue":"4","key":"3354_CR14","first-page":"5","volume":"3","author":"A Gretton","year":"2009","unstructured":"Gretton A, Smola A, Huang J et al (2009) Covariate shift by kernel mean matching. Dataset shift in machine learning 3(4):5","journal-title":"Dataset shift in machine learning"},{"key":"3354_CR15","doi-asserted-by":"crossref","unstructured":"Han K, Yu D, Tashev I (2014) Speech emotion recognition using deep neural network and extreme learning machine. In: Fifteenth Annual Conference of the International Speech Communication Association","DOI":"10.21437\/Interspeech.2014-57"},{"key":"3354_CR16","doi-asserted-by":"crossref","unstructured":"Huang Z, Xue W, Mao Q (2015) Speech emotion recognition with unsupervised feature learning. Frontiers of Information Technology & Electronic Engineering 16:358\u2013366","DOI":"10.1631\/FITEE.1400323"},{"key":"3354_CR17","doi-asserted-by":"crossref","unstructured":"Kim Y, Provost EM (2013) Emotion classification via utterance-level dynamics: A pattern-based approach to characterizing affective expressions. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 3677\u20133681","DOI":"10.1109\/ICASSP.2013.6638344"},{"key":"3354_CR18","doi-asserted-by":"crossref","unstructured":"Kim Y, Lee H, Provost EM (2013) Deep learning for robust feature generation in audiovisual emotion recognition Acoustics. In: 2013 IEEE International Conference on Speech and Signal Processing (ICASSP), pp 3687\u20133691","DOI":"10.1109\/ICASSP.2013.6638346"},{"key":"3354_CR19","doi-asserted-by":"crossref","unstructured":"Le D, Provost EM, Zhan Y (2013) Emotion recognition from spontaneous speech using hidden markov models with deep belief networks, pp 216\u2013221","DOI":"10.1109\/ASRU.2013.6707732"},{"key":"3354_CR20","unstructured":"Li L, Jin X, Long M (2012) Topic correlation analysis for cross-domain text classification. AAAI Conference on Artificial Intelligence"},{"issue":"02","key":"3354_CR21","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1142\/S0219843610002088","volume":"7","author":"Q Mao","year":"2010","unstructured":"Mao Q, Wang X, Zhan Y (2010) Speech emotion recognition method based on improved decision tree and layered feature selection. International Journal of Humanoid Robotics 7(02):245\u2013261","journal-title":"International Journal of Humanoid Robotics"},{"issue":"7","key":"3354_CR22","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1631\/jzus.CIDE1310","volume":"14","author":"Q Mao","year":"2013","unstructured":"Mao Q, Zhao X, Huang Z, Zhan Y (2013) Speaker-independent speech emotion recognition by fusion of functional and accompanying paralanguage features. Journal of Zhejiang University SCIENCE C 14(7):573\u2013582","journal-title":"Journal of Zhejiang University SCIENCE C"},{"issue":"8","key":"3354_CR23","doi-asserted-by":"crossref","first-page":"2203","DOI":"10.1109\/TMM.2014.2360798","volume":"716","author":"Q Mao","year":"2014","unstructured":"Mao Q, Dong M, Huang Z, Zhan Y (2014) Learning salient features for speech emotion recognition using convolutional neural networks. IEEE Trans Multimed 716(8):2203\u20132213","journal-title":"IEEE Trans Multimed"},{"key":"3354_CR24","doi-asserted-by":"crossref","unstructured":"Oquab M, Bottou L, Laptev I, Sivic J (2014) Learning and transferring mid-level image representations using convolutional neural networks. 2014 Proc. IEEE Conf Comput Vis Pattern Recognit (CVPR):1717\u20131724","DOI":"10.1109\/CVPR.2014.222"},{"issue":"10","key":"3354_CR25","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"S Pan","year":"2010","unstructured":"Pan S, Yang Q (2010) Survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345\u20131359","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"4","key":"3354_CR26","doi-asserted-by":"crossref","first-page":"778","DOI":"10.1109\/TASLP.2014.2303296","volume":"22","author":"R Sarikaya","year":"2014","unstructured":"Sarikaya R, Hinton GE, Deoras A (2014) Application of deep belief networks for natural language understanding. IEEE\/ACM Transactions on Audio Speech and Language Processing 22(4):778\u2013784","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"3354_CR27","doi-asserted-by":"crossref","unstructured":"Schmidt EM, Kim YE (2011) Learning emotion-based acoustic features with deep belief networks. In: 2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), pp 65\u201368","DOI":"10.1109\/ASPAA.2011.6082328"},{"key":"3354_CR28","doi-asserted-by":"crossref","unstructured":"Schuller B, Arsic D, Rigoll G, Wimmer M, Radig B (2007) Audiovisual behavior modeling by combined feature spaces. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol 2, pp II\u2013733","DOI":"10.1109\/ICASSP.2007.366340"},{"key":"3354_CR29","doi-asserted-by":"crossref","unstructured":"Schuller B, Steidl S, Batliner A (2009) The interspeech 2009 emotion challenge. In: INTERSPEECH, vol 2009, pp 312\u2013315","DOI":"10.21437\/Interspeech.2009-103"},{"issue":"2","key":"3354_CR30","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1109\/T-AFFC.2010.8","volume":"1","author":"B Schuller","year":"2010","unstructured":"Schuller B, Vlasenko B, Eyben F, Wollmer M, Stuhlsatz A, Wendemuth A, Rigoll G (2010) Cross-corpus acoustic emotion recognition: variances and strategies. IEEE Trans Affect Comput 1(2):119\u2013 131","journal-title":"IEEE Trans Affect Comput"},{"key":"3354_CR31","doi-asserted-by":"crossref","unstructured":"Swietojanski P, Ghoshal A, Renals S (2012) Unsupervised cross-lingual knowledge transfer in dnn-based lvcsr. In: 2012 IEEE Spoken Language Technology Workshop (SLT), pp 246\u2013251","DOI":"10.1109\/SLT.2012.6424230"},{"key":"3354_CR32","unstructured":"Sun Y, Wang X, Tang X (2014) Deep learning face representation by joint identification-verification. Advances in Neural Information Processing Systems:1988\u20131996"},{"key":"3354_CR33","unstructured":"Yu D, Seltzer ML, Li J, Huang JT, Seide F (2013) Feature learning in deep neural networks-studies on speech recognition tasks. arXiv preprint arXiv: 1301.3605"},{"key":"3354_CR34","doi-asserted-by":"crossref","unstructured":"Zhang B, Provost EM, Swedberg R et al (2015) Predicting emotion perception across domains: a study of singing and speaking. In: Association for the advancement of artificial intelligence, vol 2015, pp 4277\u20134280","DOI":"10.1609\/aaai.v29i1.9334"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-016-3354-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-016-3354-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-016-3354-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-016-3354-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T14:18:32Z","timestamp":1718374712000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-016-3354-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,2,22]]},"references-count":34,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2017,3]]}},"alternative-id":["3354"],"URL":"https:\/\/doi.org\/10.1007\/s11042-016-3354-x","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,2,22]]}}}