MELD

MELD is a dataset that contains multi-modal emotional dialogues used to evaluate the emotional expressiveness and prosodic features in speech synthesis.

Papers using MELD (18)

A Mixture-of-Experts Model for Multimodal Emotion Recognition in Conversations2026RLAIF-SPA: Structured AI Feedback for Semantic-Prosodic Alignment in Speech Synthesis2025On the Contribution of Lexical Features to Speech Emotion Recognition2025EmoQ: Speech Emotion Recognition via Speech-Aware Q-Former and Large Language Model2025Towards LLM-Empowered Fine-Grained Speech Descriptors for Explainable Emotion Recognition2025Vesper: A Compact and Effective Pretrained Model for Speech Emotion Recognition2023 · 3 citesExtending RNN-T-based speech recognition systems with emotion and language classification2022 · 2 citesDST: Deformable Speech Transformer for Emotion Recognition2023 · 2 citesdeep learning of segment-level feature representation for speech emotion recognition in conversations2023 · 1 citesDWFormer: Dynamic Window transFormer for Speech Emotion Recognition2023 · 1 citesA Change of Heart: Improving Speech Emotion Recognition through Speech-to-Text Modality Conversion2023 · 1 citesSpeechFormer: A Hierarchical Efficient Framework Incorporating the Characteristics of Speech2022ASR and Emotional Speech: A Word-Level Investigation of the Mutual Impact of Speech and Emotion Recognition2023MELD-ST: An Emotion-aware Speech Translation Dataset2024Multi-Scale Temporal Transformer For Speech Emotion Recognition2024WavFusion: Towards wav2vec 2.0 Multimodal Speech Emotion Recognition2024Temporal-Frequency State Space Duality: An Efficient Paradigm for Speech Emotion Recognition2024SpeechFormer++: A Hierarchical Efficient Framework for Paralinguistic Speech Processing2023