MOSI

The MOSI dataset is a benchmark that contains multimodal data for evaluating sentiment analysis and emotion recognition in spoken language.

Papers using MOSI (3)

A Mixture-of-Experts Model for Multimodal Emotion Recognition in Conversations2026ASR and Emotional Speech: A Word-Level Investigation of the Mutual Impact of Speech and Emotion Recognition2023Dawn of the transformer era in speech emotion recognition: closing the valence gap2022