Mingyang LiuYaxin KeYichen ZhangWei ShaoLinqi Song
We propose a wav2vec based speech emotion detection framework, combining features from pretrained models with neural or traditional classifiers and achieves the best performance compared with other baselines, and conduct result analysis.
P. Jothi ThilagaS KavipriyaK. Vijayalakshmi
Weishan ZhangDehai ZhaoXiufeng ChenYuanjie Zhang
Dr.G. PrathibhaYelle KavyaPierre JacobL Poojita