ML Research Wiki / Benchmarks / Speech Emotion Recognition / CREMA-D

CREMA-D

Speech Emotion Recognition Benchmark

Performance Over Time

📊 Showing 8 results | 📏 Metric: Accuracy

Top Performing Models

Rank Model Paper Accuracy Date Code
1 Vertically long patch ViT Accuracy enhancement method for speech emotion recognition from spectrogram using temporal frequency correlation and positional information learning through knowledge transfer 94.07 2024-03-26 📦 kjy7567/speech_emotion_recognition_from_log_Mel_spectrogram_using_vertically_long_patch
2 ConformerXL-P BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition 88.20 2021-09-27 -
3 SepTr + LeRaC Learning Rate Curriculum 70.95 2022-05-18 📦 croitorualin/lerac
4 SepTr SepTr: Separable Transformer for Audio Spectrogram Processing 70.47 2022-03-17 📦 ristea/septr
5 ResNet-18 + SPEL Self-paced ensemble learning for speech and audio classification 68.12 2021-03-22 -
6 ViT AST: Audio Spectrogram Transformer 67.81 2021-04-05 📦 YuanGongND/ast 📦 nttcslab/composing-general-audio-repr 📦 pxaris/ccml 📦 cgaroufis/msspt 📦 pwc-1/Paper-8
7 ResNet-18 + PyNADA Non-linear Neurons with Human-like Apical Dendrite Activations 65.15 2020-02-02 📦 raduionescu/pynada
8 GRU Visually Guided Self Supervised Learning of Speech Representations 55.01 2020-01-13 -

All Papers (8)

kjy7567/speech_emotion_recognition_from_log_Mel_spectrogram_using_vertically_long_patch

Learning Rate Curriculum

2022
SepTr + LeRaC
croitorualin/lerac
ristea/septr
YuanGongND/ast nttcslab/composing-general-audio-repr
raduionescu/pynada