Open access
Aug 2026
Bimodal Speech Emotion Recognition Using a Hybrid CNN-LSTM Architecture with Sentiment Fusion
A bimodal SER framework based on a hybrid convolutional neural network–long short-term memory (CNN–LSTM) architecture and the Multimodal EmotionLines Dataset is proposed, suggesting that class imbalance, rather than fusion complexity, remains the primary limitation in conversational SER.
Tze-Syn Yap, Lee-Yeng Ong
· Future Internet · 0 citations