TESS

The TESS dataset contains audio recordings of actors portraying various emotions and is used to evaluate speech emotion recognition models.

Papers using TESS (4)

A Novel Hybrid Deep Learning Technique for Speech Emotion Detection using Feature Engineering2025An Ensemble 1D-CNN-LSTM-GRU Model with Data Augmentation for Speech Emotion Recognition2021 · 11 citesA Comparative Study of Pre-trained Speech and Audio Embeddings for Speech Emotion Recognition2023 · 3 citesEnhanced Speech Emotion Recognition with Efficient Channel Attention Guided Deep CNN-BiLSTM Framework2024