It is becoming a mainstream feature fusion approach for speech-visual emotion recognition (SVER) by directly using neural networks to fuse the extracted speech and visual features. However, the heterogeneity between speech and visual modalities usually results in a distribution gap and information redundancy between the extracted speech and visual features, thus affecting the performance of the SVER. To this end, this paper proposes a SVER method based on the modal decomposition learning. It leverages the shared, private and reconstructed modal learning with a specifically designed loss to decompose the extracted speech and visual features into the shared and private subspaces to obtain the shared and private features, which effectively reduces the distribution gap and information redundancy between the extracted speech and visual features. Experiments on the BAUM-1s, RAVDESS and eNTERFACE05 datasets also show that the proposed method achieves a better result.

In order to select the proper cloud manufacturing services to satisfy both sides of supplier and demander, a bi-level programming model is proposed based on extension theory in this paper. Firstly, the cloud model is employed to convert qualitative concepts of language description into quantitative values. Then, according to multicriteria assessment information, the satisfactions of both providers and demanders are calculated by extension evaluation. Finally, respectively taking satisfactions of the demanders and providers as optimization goal of upper layer and lower layer, a mathematical model of bi-level programming is constructed which is solved by linear programming. Compared with traditional recommended methods, the proposed method takes full account of the interests of service providers which have long been neglected. Moreover, extension evaluation is applied to reflect the demand and preference of each subject in detail. Experimental results verify the effectiveness and applicability of the proposed model.