{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T00:45:37Z","timestamp":1767141937413,"version":"build-2238731810"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2019,5,2]],"date-time":"2019-05-02T00:00:00Z","timestamp":1556755200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Autom. Comput."],"published-print":{"date-parts":[[2019,8]]},"DOI":"10.1007\/s11633-019-1175-x","type":"journal-article","created":{"date-parts":[[2019,5,2]],"date-time":"2019-05-02T01:02:27Z","timestamp":1556758947000},"page":"437-448","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Semi-supervised Ladder Networks for Speech Emotion Recognition"],"prefix":"10.1007","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9437-7188","authenticated-orcid":false,"given":"Jian-Hua","family":"Tao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ya","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Lian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming-Yue","family":"Niu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,5,2]]},"reference":[{"key":"1175_CR1","doi-asserted-by":"crossref","first-page":"981","DOI":"10.1007\/11573548_125","volume-title":"Proceedings of the 1st International Conference on Affective Computing and Intelligent Interaction","author":"J H Tao","year":"2005","unstructured":"J. H. Tao, T. N. Tan. Affective computing: A review. In Proceedings of the 1st International Conference on Affective Computing and Intelligent Interaction, Springer, Beijing, China, pp. 981\u2013995, 2005. DOI: 11.1007\/11573548_125."},{"key":"1175_CR2","first-page":"2202","volume-title":"Proceedings of the 11th Annual Conference of the International Speech Communication Association","author":"H Bo\u0159il","year":"2010","unstructured":"H. Bo\u0159il, A. Sangwan, T. Hasan, J. H. Hansen. Automatic excitement-level detection for sports highlights generation. In Proceedings of the 11th Annual Conference of the International Speech Communication Association, ISCA, Makuhari, Japan, pp. 2202\u20132205, 2010."},{"issue":"2","key":"1175_CR3","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1016\/j.imavis.2012.06.016","volume":"31","author":"H Gunes","year":"2013","unstructured":"H. Gunes, B. Schuller. Categorical and dimensional affect analysis in continuous input: current trends and future directions. Image and Vision Computing, vol. 31, no. 2, pp. 120\u2013136, 2013. DOI: \nhttps:\/\/doi.org\/10.1016\/j.imavis.2012.06.016\n\n.","journal-title":"Image and Vision Computing"},{"issue":"4","key":"1175_CR4","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1016\/S0167-6313(03)00011-2","volume":"41","author":"T L Nwe","year":"2003","unstructured":"T. L. Nwe, S. W. Foo, L. C. De Silva. Speech emotion recognition using hidden Markov models. Speech Communication, vol 41, no. 4, pp. 603\u2013623, 2003. DOI: \nhttps:\/\/doi.org\/10.1016\/S0167-6313(03)00011-2\n\n.","journal-title":"Speech Communication"},{"key":"1175_CR5","doi-asserted-by":"publisher","first-page":"957","DOI":"10.1109\/ICASSP.2007.367230","volume-title":"Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing","author":"M M H El Ayadi","year":"2007","unstructured":"M. M. H. El Ayadi, M. S. Kamel, F. Karray. Speech emotion recognition using Gaussian mixture vector autoregressive models. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, Honolulu, USA, pp. 957\u2013960, 2007. DOI: \nhttps:\/\/doi.org\/10.1109\/ICASSP.2007.367230\n\n."},{"issue":"1","key":"1175_CR6","doi-asserted-by":"publisher","first-page":"1068","DOI":"10.1109\/LSP.2014.2324751","volume":"21","author":"J Deng","year":"2014","unstructured":"J. Deng, Z. X. Zhang, F. Eyben, B. Schuller. Autoencoder-based unsupervised domain adaptation for speech emotion recognition. IEEE Signal Processing Letters, vol. 21, no. 1, pp. 1068\u20131072, 2014. DOI: \nhttps:\/\/doi.org\/10.1109\/LSP.2014.2324751\n\n.","journal-title":"IEEE Signal Processing Letters"},{"issue":"2","key":"1175_CR7","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/s11633-017-1053-3","volume":"14","author":"B Zhao","year":"2017","unstructured":"B. Zhao, J. S. Feng, X. Wu, S. C. Yan. A survey on deep learning-based fine-grained object classification and semantic segmentation. International Journal of Automation and Computing, vol. 14, no. 2, pp. 111\u2013135, 2017. DOI: \nhttps:\/\/doi.org\/10.1007\/s11633-017-1053-3\n\n.","journal-title":"International Journal of Automation and Computing"},{"issue":"6","key":"1175_CR8","doi-asserted-by":"publisher","first-page":"643","DOI":"10.1007\/s11633-018-1136-1","volume":"15","author":"Z J Yao","year":"2018","unstructured":"Z. J. Yao, J. Bi, Y. X. Chen. Applying deep learning to individual and community health monitoring data: a survey. International Journal of Automation and Computing, vol. 15, no. 6, pp. 643\u2013655, 2018. DOI: \nhttps:\/\/doi.org\/10.1007\/s11633-018-1136-1\n\n.","journal-title":"International Journal of Automation and Computing"},{"key":"1175_CR9","first-page":"1263","volume-title":"Proceedings of the 18th Annual Conference of the International Speech Communication Association","author":"M Neumann","year":"2017","unstructured":"M. Neumann, N. T. Vu. Attentive convolutional neural network based speech emotion recognition: A study on the impact of input features, signal length, and acted speech. In Proceedings of the 18th Annual Conference of the International Speech Communication Association, ISAA, Stockholm, Sweden, pp. 1263\u20131267, 2017."},{"key":"1175_CR10","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.neunet.2017.02.013","volume":"12","author":"H M Fayek","year":"2017","unstructured":"H. M. Fayek, M. Lech, L. Cavedon. Evaluating deep learning architectures for speech emotion recognition. Neural Networks, vol. 12, pp. 60\u201368, 2017. DOI: \nhttps:\/\/doi.org\/10.1016\/j.neunet.2017.02.013\n\n.","journal-title":"Neural Networks"},{"key":"1175_CR11","doi-asserted-by":"publisher","first-page":"2274","DOI":"10.1101\/ICASSP.2016.7472082","volume-title":"Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing","author":"S E Eskimez","year":"2016","unstructured":"S. E. Eskimez, K. Imade, N. Yang, M. Sturge-Apple, Z. Y. Duan, W. Heinzelman. Emotion classification: How does an automated system compare to Naive human coders? In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, Shanghai, China, pp. 2274\u20132278, 2016. DOI: \nhttps:\/\/doi.org\/10.1101\/ICASSP.2016.7472082\n\n."},{"key":"1175_CR12","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1145\/2647868.2656408","volume-title":"Proceedings of the 22nd ACM International Conference on Multimedia","author":"B Jou","year":"2014","unstructured":"B. Jou, S. Bhattacharya, S. F. Chang. Predicting viewer perceived emotions in animated GIFs. In Proceedings of the 22nd ACM International Conference on Multimedia, Drlando, USA, pp.213\u2013216, 2014. DOI: \nhttps:\/\/doi.org\/10.1145\/2647868.2656408\n\n."},{"issue":"3","key":"1175_CR13","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1016\/j.patcog.2010.01.020","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 Recognition, vol. 44, no. 3, pp. 572\u2013587, 2011. DOI: \nhttps:\/\/doi.org\/10.1016\/j.patcog.2010.01.020\n\n.","journal-title":"Pattern Recognition"},{"issue":"12","key":"1175_CR14","first-page":"3371","volume":"11","author":"P Vincent","year":"2010","unstructured":"P. Vincent, H. Larochelle, I. Lajoie, Y. Bengio. Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of Machine Learning Research, vol. 11, no. 12, pp. 3371\u20133408, 2010.","journal-title":"Journal of Machine Learning Research"},{"issue":"5786","key":"1175_CR15","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"G E Hinton","year":"2006","unstructured":"G. E. Hinton, R. R. Salakhutdinov. Reducing the dimensionality of data with neural networks. Science, vol. 313, no. 5786, pp. 504\u2013507, 2006. DOI: \nhttps:\/\/doi.org\/10.1126\/science.1127647\n\n.","journal-title":"Science"},{"key":"1175_CR16","volume-title":"Proceedings of the 2nd International Conference on Learning Representations","author":"D P Kingma","year":"2013","unstructured":"D. P. Kingma, M. Welling. Auto-encoding variational Bayes. In Proceedings of the 2nd International Conference on Learning Representations, ICLR, Ithaca, USA, 2013."},{"key":"1175_CR17","first-page":"2672","volume-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems","author":"I J Goodfellow","year":"2014","unstructured":"I. J. Goodfellow, J. Pouget-Abadie, M Mirza, B. Xu, D. Warde-Farley, S. Dzair, A. Courville, Y. Bengio. Generative adversarial nets. In Proceedings of the 27th International Conference on Neural Information Processing Systems, MIT Press, Montreal, Canada, pp. 2672\u20132680, 2014."},{"key":"1175_CR18","first-page":"3546","volume-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems","author":"A Rasmin","year":"2015","unstructured":"A. Rasmin, H. Valpola, M. Honkala, M. Berglund, T. Raiko. Semi-supervised learning with ladder networks. In Proceedings of the 28th International Conference on Neural Information Processing Systems, MIT Press, Montreal, Canada, pp. 3546\u20133554, 2015."},{"key":"1175_CR19","doi-asserted-by":"publisher","first-page":"631","DOI":"10.1007\/178-3-642-35281-8_34","volume-title":"Neural Networks: Tricks of the Trade","author":"J Weston","year":"2012","unstructured":"J. Weston, F. Ratle, H. Mobahi, R. Collobert. Deep learning via, semi-supervised embedding. Neural Networks: Tricks of the Trade, 2nd ed., G. Montavon, G. B. Orr, K. R. M\u00fcller, Eds., Berlin Heidelberg, Germany: Springer, pp. 631\u2013655, 2012. DOI: \nhttps:\/\/doi.org\/10.1007\/178-3-642-35281-8_34\n\n.","edition":"2nd ed."},{"key":"1175_CR20","first-page":"3581","volume-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems","author":"D P Kingma","year":"2014","unstructured":"D. P. Kingma, D. J. Rezende, S. Mohamed, M. Welling. Semi-supervised learning with deep generative models. In Proceedings of the 27th International Conference on Neural Information Processing Systems, MIT Press, Montreal, Canada, pp. 3581\u20133581, 2014."},{"key":"1175_CR21","first-page":"110","volume-title":"Social Emotions in Nature and Artifact: Emotions in Human and Human Computer Interaction","author":"C Busso","year":"2014","unstructured":"C. Busso, M. Bulut, S. Narayanan. Toward effective automatic recognition systems of emotion in speech. Social Emotions in Nature and Artifact: Emotions in Human and Human Computer Interaction, J. Gratch and S. Marsella, Eds., New York, USA: Oxford University Press, pp. 110\u2013127, 2014."},{"key":"1175_CR22","first-page":"1103","volume-title":"Proceedings of the 18th Annual Conference of the International Speech Communication Association","author":"S Parthasarathy","year":"2017","unstructured":"S. Parthasarathy, C. Busso. Jointly predicting arousal, valence and dominance with multi-task learning. In Proceedings of the 18th Annual Conference of the International Speech Communication Association, ISCA, Stockholm, Sweden, pp. 1103\u20131107, 2017."},{"key":"1175_CR23","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1007\/978-3-540-74122-0_5","volume-title":"Speaker Classification II: Selected Projects","author":"M Shami","year":"2007","unstructured":"M. Shami, W. Verhelst. Automatic classification of expressiveness in speech: a multi-corpus study. Speaker Classification II: Selected Projects, C. M\u00fcller, Ed., Berlin Heidelberg, Germany: Springer-Verlag, vol. 4441, pp. 43\u201356, 2007. DOI: \nhttps:\/\/doi.org\/10.1007\/978-3-540-74122-0_5\n\n."},{"key":"1175_CR24","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/B978-0-12-802806-3.00008-7","volume-title":"Advances in Independent Component Analysis and Learning Machines","author":"H Valpola","year":"2015","unstructured":"H. Valpola. From neural PCA to deep unsupervised learning. Advances in Independent Component Analysis and Learning Machines, E. Bingham, S. Kaski, J. Laaksonen, J. Lampinen, Eds., Amsterdam, Netherlands: Academic Press, pp. 143\u2013171, 2015. DOI: \nhttps:\/\/doi.org\/10.1016\/B978-0-12-802806-3.00008-7\n\n."},{"issue":"1","key":"1175_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2200000006","volume":"2","author":"Y Bengio","year":"2009","unstructured":"Y. Bengio. Learning deep architectures for AI. Foundations and Trends in Machine Learning, vol. 2, no. 1, pp. 1\u2013127, 2009. DOI: \nhttps:\/\/doi.org\/10.1561\/2200000006\n\n.","journal-title":"Foundations and Trends in Machine Learning"},{"issue":"2","key":"1175_CR26","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/TAFFC.2015.2457417","volume":"7","author":"F Eyben","year":"2016","unstructured":"F. Eyben, K. R. Scherer, B. W. Schuller, J. Sundberg, E. Andr\u00e9, C. Busso, L. Y. Devillers, J. Epps, P. Laukka, S. S. Narayanan, K. P. Truong. The Geneva minimalistic acoustic parameter set (GeMAPS) for voice research and affective computing. IEEE Transactions on Affective Computing, vol. 7, no. 2, pp. 190\u2013202, 2016. DOI: \nhttps:\/\/doi.org\/10.1109\/TAFFC.2015.2457417\n\n.","journal-title":"IEEE Transactions on Affective Computing"},{"key":"1175_CR27","volume-title":"Proceedings of the 3nd International Workshop on Affective Social Multimeda Computing","author":"J Huang","year":"2017","unstructured":"J. Huang, Y. Li, J. H. Tao. Effect of dimensional emotion in discrete speech emotion classification. In Proceedings of the 3nd International Workshop on Affective Social Multimeda Computing, ASMMC, Stockholm, Sweden, 2017."},{"key":"1175_CR28","doi-asserted-by":"publisher","first-page":"3687","DOI":"10.1109\/ICASSP.2013.6638346","volume-title":"Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing","author":"Y Kim","year":"2013","unstructured":"Y. Kim, H. Lee, E. M. Provost. Deep learning for robust feature generation in audiovisual emotion recognition. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, Canada, pp. 3687\u20133691, 2013. DOI: \nhttps:\/\/doi.org\/10.1109\/ICASSP.2013.6638346\n\n."},{"key":"1175_CR29","doi-asserted-by":"publisher","first-page":"4818","DOI":"10.1109\/ICASSP.2014.6854517","volume-title":"Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing","author":"J Deng","year":"2014","unstructured":"J. Deng, R. Xia, Z. X. Zhang, Y. Liu, B. Schuller. Introducing shared-hidden-layer autoencoders for transfer learning and their application in acoustic emotion recognition. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, Florence, Italy, pp. 4818\u20134822, 2014. DOI: \nhttps:\/\/doi.org\/10.1109\/ICASSP.2014.6854517\n\n."},{"key":"1175_CR30","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1109\/ACII.2013.90","volume-title":"Proceedings of Humaine Association Conference on Affective Computing and Intelligent Interaction","author":"J Deng","year":"2013","unstructured":"J. Deng, Z. X. Zhang, E. Marchi, B. Schuller. Sparse autoencoder-based feature transfer learning for speech emotion recognition. In Proceedings of Humaine Association Conference on Affective Computing and Intelligent Interaction, IEEE, Geneva, Switzerland, pp. 511\u2013516, 2013. DOI: \nhttps:\/\/doi.org\/10.1109\/ACII.2013.90\n\n."},{"key":"1175_CR31","first-page":"2886","volume-title":"Proceedings of the 14th Annual Conference of the International Speech Communication Association","author":"R Xia","year":"2013","unstructured":"R. Xia, Y. Liu. Using denoising autoencoder for emotion recognition. In Proceedings of the 14th Annual Conference of the International Speech Communication Association, ISCA, Lyon, France, pp. 2886\u20132889, 2013."},{"key":"1175_CR32","doi-asserted-by":"publisher","first-page":"990","DOI":"10.1109\/ICASSP.2014.6853745","volume-title":"Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing","author":"R Xia","year":"2014","unstructured":"R. Xia, J. Deng, B. Schuller, Y. Liu. Modeling gender information for emotion recognition using denoising autoencoder. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, Florence, Italy, pp. 990\u2013994, 2014. DOI: \nhttps:\/\/doi.org\/10.1109\/ICASSP.2014.6853745\n\n."},{"key":"1175_CR33","volume-title":"Proceedings of International Conference on Learning Representations","author":"S Ghosh","year":"2016","unstructured":"S. Ghosh, E. Laksana, L. P. Morency, S. Scherer. Learning representations of affect from speech. In Proceedings of International Conference on Learning Representations, ICLR, San Juan, Puerto Rico, 2016."},{"key":"1175_CR34","first-page":"3603","volume-title":"Proceedings of the 17th Annual Conference of the International Speech Communication Association","author":"S Ghosh","year":"2016","unstructured":"S. Ghosh, E. Laksana, L. P. Morency, S. Scherer. Representation learning for speech emotion recognition. In Proceedings of the 17th Annual Conference of the International Speech Communication Association, ISCA, San Francisco, USA, pp. 3603\u20133607, 2016."},{"key":"1175_CR35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462685","volume-title":"Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing","author":"S E Eskimez","year":"2018","unstructured":"S. E. Eskimez, Z. Y. Duan, W. Heinzelman. Unsupervised learning approach to feature analysis for automatic speech emotion recognition. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, Calgary, Canada, 2018. DOI: \nhttps:\/\/doi.org\/10.1109\/ICASSP.2018.8462685\n\n."},{"issue":"1","key":"1175_CR36","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1109\/TASLP.2017.2759338","volume":"26","author":"J Deng","year":"2018","unstructured":"J. Deng, X. Z. Xu, Z. X. Zhang, S. Fr\u00fchholz, B. Schuller. Semisupervised autoencoders for speech emotion recognition. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, vol. 26, no. 1, pp. 31\u201343, 2018. DOI: \nhttps:\/\/doi.org\/10.1109\/TASLP.2017.2759338\n\n.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"1175_CR37","unstructured":"A. Rasmus, H. Valpola, T. Raiko. Lateral Connections in Denoising Autoencoders Support Supervised Learning, [Online], Available: \nhttps:\/\/arxiv.org\/abs\/1504.08215\n\n, April, 2015."},{"key":"1175_CR38","first-page":"2368","volume-title":"Proceedings of the 33rd International Conference on International Conference on Machine Learning","author":"M Pezeshki","year":"2016","unstructured":"M. Pezeshki, L. X. Fan, P. Brakel, A. Courville, Y. Bengio. Deconstructing the ladder network architecture. In Proceedings of the 33rd International Conference on International Conference on Machine Learning, ACM, New York, USA, pp. 2368\u20132376, 2016."},{"key":"1175_CR39","doi-asserted-by":"publisher","DOI":"10.1109\/ACII-Asia.2018.8470363","volume-title":"Proceedings of the 1st Asian Conference on Affective Computing and Intelligent Interaction","author":"J Huang","year":"2018","unstructured":"J. Huang, Y. Li, J. H. Tao, Z. Lian, M. Y. Niu, J. Y. Yi. Speech emotion recognition using semi-supervised learning with ladder networks. In Proceedings of the 1st Asian Conference on Affective Computing and Intelligent Interaction, IEEE, Beijing, China, 2018. DOI: \nhttps:\/\/doi.org\/10.1109\/ACII-Asia.2018.8470363\n\n."},{"key":"1175_CR40","doi-asserted-by":"crossref","unstructured":"S. Parthasarathy, C. Busso. Ladder Networks for Emotion Recognition: Using Unsupervised Auxiliary Tasks to Improve Predictions of Emotional Attributes, [Online], Available: \nhttps:\/\/www.isca-speech.org\/archive\/Inter-speech_2018\/abstracts\/1391.html\n\n, 2018.","DOI":"10.21437\/Interspeech.2018-1391"},{"issue":"4","key":"1175_CR41","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, J. N. Chang, S. Lee, S. S. Narayanan. IEMOCAP: interactive emotional dyadic motion capture database. Language Resources and Evaluation, vol. 42, no. 4, pp. 335\u2013359, 2008. DOI: \nhttps:\/\/doi.org\/10.1007\/s10579-008-9076-6\n\n.","journal-title":"Language Resources and Evaluation"},{"key":"1175_CR42","first-page":"312","volume-title":"Proceedings of the 10th Annual Conference of the International Speech Communication Association","author":"B Schuller","year":"2009","unstructured":"B. Schuller, S. Steidl, A. Batliner. The Interspeech 2009 emotion challenge. In Proceedings of the 10th Annual Conference of the International Speech Communication Association, ISCA, Brighton, UK, pp. 312\u2013315, 2009."},{"key":"1175_CR43","doi-asserted-by":"publisher","first-page":"1459","DOI":"10.1145\/1873951.1874246","volume-title":"Proceedings of the 18th ACM International Conference on Multimedia","author":"F Eyben","year":"2010","unstructured":"F. Eyben, M. W\u00f6llmer, B. Schuller. Opensmile: The Munich versatile and fast open-source audio feature extractor. In Proceedings of the 18th ACM International Conference on Multimedia, ACM, Florence, Italy, pp. 1459\u20131462, 2010. DOI: \nhttps:\/\/doi.org\/10.1145\/1873951.1874246\n\n."},{"key":"1175_CR44","volume-title":"Proceedings of International Conference on Learning Representations","author":"D P Kingma","year":"2015","unstructured":"D. P. Kingma, J. L. Ba. Adam: A method for stochastic optimization. In Proceedings of International Conference on Learning Representations, ICLR, Ithaca, USA, 2015."}],"updated-by":[{"DOI":"10.1007\/s11633-019-1215-6","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2019,12,13]],"date-time":"2019-12-13T00:00:00Z","timestamp":1576195200000}}],"container-title":["International Journal of Automation and Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11633-019-1175-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11633-019-1175-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11633-019-1175-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,30]],"date-time":"2020-04-30T19:51:13Z","timestamp":1588276273000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11633-019-1175-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,2]]},"references-count":44,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2019,8]]}},"alternative-id":["1175"],"URL":"https:\/\/doi.org\/10.1007\/s11633-019-1175-x","relation":{},"ISSN":["1476-8186","1751-8520"],"issn-type":[{"value":"1476-8186","type":"print"},{"value":"1751-8520","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,5,2]]},"assertion":[{"value":"12 October 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 March 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 May 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 December 2019","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The article Semi-supervised Ladder Networks for Speech Emotion Recognition written by Jian-Hua Tao, Jian Huang, Ya Li, Zheng Lian and Ming-Yue Niu, was originally published on vol. 16, no. 4 of <Emphasis Type=\"Italic\">International Journal of Automation and Computing<\/Emphasis> without Open Access. After publication, the authors decided to opt for Open Choice and to make the article an Open Access publication. Therefore, the copyright of the article has been changed to \u00a9 The Author(s) 2019 and the article is forthwith distributed under the terms of the Creative Commons Attribution 4.0 International License (http:\/\/creativecommons.org\/licenses\/by\/4.0\/), which permits use, duplication, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}}]}}