Multi-stream Attention-based BLSTM with Feature Segmentation for Speech Emotion Recognition

no code implementations • Interspeech 2020 • Yuya Chiba1, Takashi Nose1, Akinori Ito

One of the model’s weaknesses is that it cannot consider the statistics of speech features, which are known to be effective for speech emotion recognition.

Data Augmentation Emotional Speech Synthesis +1