Machine learning (ML) models can accurately identify emotions from brief audio clips, achieving a level of accuracy comparable to humans. By analyzing nonsensical sentences to remove the influence of language and content, the study found that deep neural networks (DNNs) and a hybrid model (C-DNN) were particularly effective in recognizing emotions such as joy, anger, sadness, and fear from clips as short as 1.5 seconds.
Source NeuroScienceNews
