RAVDESS

The RAVDESS dataset is a benchmark that contains emotional speech recordings used to evaluate paralinguistic understanding in speech large language models.

Papers using RAVDESS (15)

EmoHRNet: High-Resolution Neural Network Based Speech Emotion Recognition2025 · 2 citesAligning Paralinguistic Understanding and Generation in Speech LLMs via Multi-Task Reinforcement Learning2026Enhancing Speech Emotion Recognition using Dynamic Spectral Features and Kalman Smoothing2026Multi-Loss Learning for Speech Emotion Recognition with Energy-Adaptive Mixup and Frame-Level Attention2025Enhancing Speech Emotion Recognition via Fine-Tuning Pre-Trained Models and Hyper-Parameter Optimisation2025EmoAugNet: A Signal-Augmented Hybrid CNN-LSTM Framework for Speech Emotion Recognition2025A Novel Hybrid Deep Learning Technique for Speech Emotion Detection using Feature Engineering2025Exploring Multilingual Unseen Speaker Emotion Recognition: Leveraging Co-attention Cues In Multitask Learning2024 · 3 citesImprovement And Implementation Of A Speech Emotion Recognition Model Based On Dual-layer LSTM2024 · 1 citesEmodiarize: Speaker Diarization And Emotion Identification From Speech Signals Using Convolutional Neural Networks2023Exploring Multilingual Unseen Speaker Emotion Recognition: Leveraging Co-Attention Cues in Multitask Learning2024 · 1 citesImprovement and Implementation of a Speech Emotion Recognition Model Based on Dual-Layer LSTM2024 · 1 citesSELM: Enhancing Speech Emotion Recognition for Out-of-Domain Scenarios2024Enhanced Speech Emotion Recognition with Efficient Channel Attention Guided Deep CNN-BiLSTM Framework2024Modulation spectral features for speech emotion recognition using deep neural networks2023