paper-with-me

Speech Emotion Recognition 벤치마크

Speech Emotion Recognition on RAVDESS

13개 결과 · ⬇ CSV · JSON

Accuracy

61.67 70.03 78.38 86.74 95.1 2020-07 2026-09 CNN-X (Shallow CNN) — 82.99 (2020-07-03) CNN-X (Shallow CNN) — 82.99 (2020-07-03) CNN-14 (Fine-Tuning) — 76.58 (2021-11-18) AlexNet (FineTuning) — 61.67 (2021-11-18) CNN-14 (Fine-Tuning) — 76.58 (2021-11-18) AlexNet (FineTuning) — 61.67 (2021-11-18) xlsr-Wav2Vec2.0(FineTuning) — 81.82 (2021-12-30) xlsr-Wav2Vec2.0(FineTuning) — 81.82 (2021-12-30) VQ-MAE-S-12 (Frame) + Query2Emo — 84.1 (2023-04-21) VQ-MAE-S-12 (Frame) + Query2Emo — 84.1 (2023-04-21) DCRF-BiLSTM — 95.1 (2025-07-09) EmoAugNet — 91.28 (2025-08-06) Distilled HuBERT for Mobile Speech Emoti — 91.0 (2025-12-29) CNN-X (Shallow CNN) — 82.99 (2020-07-03) VQ-MAE-S-12 (Frame) + Query2Emo — 84.1 (2023-04-21) DCRF-BiLSTM — 95.1 (2025-07-09)
RankModel AccuracyF1 ScorePrecisionRecallF1 Extra Training Data PaperCodeYear
1 DCRF-BiLSTM 자동 추출 95.10–––– A Novel Hybrid Deep Learning Technique for Speech Emotion Detection using Feature Engineering 2025
2 EmoAugNet 자동 추출 91.28–––– EmoAugNet: A Signal-Augmented Hybrid CNN-LSTM Framework for Speech Emotion Recognition 2025
3 Distilled HuBERT for Mobile Speech Emoti 자동 추출 91–––– Distilled HuBERT for Mobile Speech Emotion Recognition: A Cross-Corpus Validation Study 2025
4 VQ-MAE-S-12 (Frame) + Query2Emo 84.1–––0.844 A vector quantized masked autoencoder for speech emotion recognition samsad35/VQ-MAE-S-code 2023
5 CNN-X (Shallow CNN) 82.99%0.820.820.82– Shallow over Deep Neural Networks: A empirical analysis for human emotion classification using audio data 2020
6 xlsr-Wav2Vec2.0(FineTuning) 81.82%–––– ✓ A proposal for Multimodal Emotion Recognition using aural transformers and Action Units on RAVDESS dataset cristinalunaj/MMEmotionRecognition 2021
7 CNN-14 (Fine-Tuning) 76.58%–––– ✓ Multimodal Emotion Recognition on RAVDESS Dataset Using Transfer Learning 2021
8 AlexNet (FineTuning) 61.67%–––– ✓ Multimodal Emotion Recognition on RAVDESS Dataset Using Transfer Learning 2021
9 VQ-MAE-S-12 (Frame) + Query2Emo 84.1–––0.844 A vector quantized masked autoencoder for speech emotion recognition samsad35/VQ-MAE-S-code 2023
10 CNN-X (Shallow CNN) 82.99%0.820.820.82– Shallow over Deep Neural Networks: A empirical analysis for human emotion classification using audio data 2020
11 xlsr-Wav2Vec2.0(FineTuning) 81.82%–––– ✓ A proposal for Multimodal Emotion Recognition using aural transformers and Action Units on RAVDESS dataset cristinalunaj/MMEmotionRecognition 2021
12 CNN-14 (Fine-Tuning) 76.58%–––– ✓ Multimodal Emotion Recognition on RAVDESS Dataset Using Transfer Learning 2021
13 AlexNet (FineTuning) 61.67%–––– ✓ Multimodal Emotion Recognition on RAVDESS Dataset Using Transfer Learning 2021
1–13 / 13 페이지당 10 20 50 100