emotion2vec+large

Reported on 6 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio3 results

Emotion RecognitiononRESD
Unweighted Accuracy (UA)· 2023-12-23
69.1
best: 79.8 (emotion2vec+base)
emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation arXiv:2312.15185
Emotion RecognitiononRESD
Weighted Accuracy (WA)· 2023-12-23
69.5
best: 79.4 (emotion2vec+base)
emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation arXiv:2312.15185
Emotion RecognitiononRESD
Weighted F1· 2023-12-23
68.8
best: 79.4 (emotion2vec+base)
emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation arXiv:2312.15185

Speech3 results

Speech Emotion RecognitiononRESD
Unweighted Accuracy (UA)· 2023-12-23
69.1
best: 79.8 (emotion2vec+base)
emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation arXiv:2312.15185
Speech Emotion RecognitiononRESD
Weighted Accuracy (WA)· 2023-12-23
69.5
best: 79.4 (emotion2vec+base)
emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation arXiv:2312.15185
Speech Emotion RecognitiononRESD
Weighted F1· 2023-12-23
68.8
best: 79.4 (emotion2vec+base)
emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation arXiv:2312.15185