A Deep Learning Approach Toward Analyzing the Cross‐Lingual Acoustic‐Phonetic Similarities in Multilingual Speech Emotion Recognition

This study uses deep learning to explore the influence of phonetic similarities across languages on multilingual SER systems in diverse linguistic contexts. A deep convolutional neural network (DCNN) model was employed to evaluate the performance of speech emotion detection in a multilingual context. Experimented datasets are the SUST Bangla Emotional Speech Corpus (SUBESCO), Indian Institute of Technology Kharagpur Simulated Emotion Hindi Speech Corpus (IITKGP‐SEHSC), SIT Bhubaneswar‐Odia Speech Emotion Database (SITB‐OSED), Ryerson Audio‐Visual Database of Emotional Speech and Song (RAVDESS), and EmoDB datasets of Bangla, Hindi, Odia, English, and German languages, respectively. Here, Bangla, Hindi, and Odia are of the Indo‐Aryan language family and English and German are of the Germanic. A baseline monolingual experiment was performed first to evaluate the models, and then cross‐lingual and multilingual experiments were carried out. The experimental results reveal that the models can recognize emotions of multiple language speech of the same linguistic family better than language speech from different families. The DCNN model achieved the highest multilingual emotion recognition accuracy of 83% for Indo‐Aryan languages, 79% for Germanic languages, and 73% when both language families were combined. These results suggest that phonetic similarities within the same language family improve recognition accuracy.