MSP-Improv

The MSP-IMPROV dataset is a benchmark for evaluating speech emotion recognition systems, containing diverse speech samples that capture various emotional expressions.

Papers using MSP-Improv (9)

Multi-Loss Learning for Speech Emotion Recognition with Energy-Adaptive Mixup and Frame-Level Attention2025Speech Emotion Recognition via Entropy-Aware Score Selection2025CTA-RNN: Channel and Temporal-wise Attention RNN Leveraging Pre-trained ASR Embeddings for Speech Emotion Recognition2022 · 2 citesReal-time Speech Emotion Recognition Based on Syllable-Level Feature Extraction2022 · 1 citesSemi-FedSER: Semi-supervised Learning for Speech Emotion Recognition On Federated Learning using Multiview Pseudo-Labeling2022Multitask Learning from Augmented Auxiliary Data for Improving Speech Emotion Recognition2022Enhancing Speech Emotion Recognition Through Differentiable Architecture Search2023Integrating Contrastive Learning into a Multitask Transformer Model for Effective Domain Adaptation2023emoDARTS: Joint Optimisation of CNN & Sequential Neural Network Architectures for Superior Speech Emotion Recognition2024