Improving multilingual speech emotion recognition by combining acoustic features in a three-layer model

•We study multilingual speech emotion recognition (mSER) by combined acoustic features in a three-layer perceptual emotion model.•We analyze three vital issues: 1) robust features to mSER; 2) impact of speaker normalization (SN); (3) generalization of mSER to a new language.•Prosody and modulation spectrum features are studied. Z-normalization forms SN. Cross-speaker and -corpus tasks enhance the robustness of mSER.•The proposed mSER model outperforms previous works. Notably, it allows a comparable result to monolingual SER in a new language without training.