Speech Emotion Diarization

Speech Emotion Diarization (SED) aims to identify which emotions are expressed and when they occur within a speech recording, moving beyond simple utterance-level emotion recognition. Current research focuses on developing robust models, often employing deep learning techniques, to accurately segment and classify emotional segments, sometimes incorporating multimodal data like audio and vibration signals. This work is significant for advancing both fundamental understanding of human emotion expression and for practical applications in areas like human-computer interaction, mental health monitoring, and personalized user experiences.