The IEMOCAP database is a new audio-visual corpus designed to study emotional expression through speech and gestures. It was collected by the Speech Analysis and Interpretation Laboratory at the University of Southern California. The database includes motion capture data from ten actors in dyadic sessions, with markers on their faces, heads, and hands, providing detailed information about facial expressions and hand movements during scripted and spontaneous communication scenarios. The actors performed selected emotional scripts and improvised hypothetical scenarios to elicit specific emotions (happiness, anger, sadness, frustration, and neutral state). The corpus contains approximately 12 hours of data. The detailed motion capture information, interactive setting for authentic emotion elicitation, and database size make it a valuable resource for studying multimodal and expressive human communication. Existing databases often lack genuine interaction, integrated information from multiple channels, and sufficient data size. The IEMOCAP database addresses these limitations by including detailed motion capture data, allowing for more accurate analysis of gestures. The database was collected over 20 months and is hoped to contribute to the advancement of research in emotional communication.The IEMOCAP database is a new audio-visual corpus designed to study emotional expression through speech and gestures. It was collected by the Speech Analysis and Interpretation Laboratory at the University of Southern California. The database includes motion capture data from ten actors in dyadic sessions, with markers on their faces, heads, and hands, providing detailed information about facial expressions and hand movements during scripted and spontaneous communication scenarios. The actors performed selected emotional scripts and improvised hypothetical scenarios to elicit specific emotions (happiness, anger, sadness, frustration, and neutral state). The corpus contains approximately 12 hours of data. The detailed motion capture information, interactive setting for authentic emotion elicitation, and database size make it a valuable resource for studying multimodal and expressive human communication. Existing databases often lack genuine interaction, integrated information from multiple channels, and sufficient data size. The IEMOCAP database addresses these limitations by including detailed motion capture data, allowing for more accurate analysis of gestures. The database was collected over 20 months and is hoped to contribute to the advancement of research in emotional communication.