About IEMOCAP Accuracy

[JYeonKim]

Hi, I have a question. Obviously I know that the IEMOCAP dataset is multi-label, but if you look at the code, it seems that the accuracy was measured with single-label method. Maybe I misunderstood the code?

If you don't mind, can you explain it to me?

Thank you

[Vincent-ZHQ]

There are serval methods to use the IEMOCAP dataset. This paper is a four-class classification task and uses the final decided emotions as labels. In some papers, they use all voted emotions and treat it as a multi-label classification task. The emotion classes could also be different in different tasks. I think you have to check the original paper with the help of the raw dataset.