Transfer Learning based Speech Affect Recognition in Urdu

no code implementations • 5 Mar 2021 • Sara Durrani, Muhammad Umair Arshad

Here we present a Transfer learning based Speech Affect Recognition approach in which: we pre-train a model for high resource language affect recognition task and fine tune the parameters for low resource language using Deep Residual Network.

Transfer Learning

Transfer learning from High-Resource to Low-Resource Language Improves Speech Affect Recognition Classification Accuracy

no code implementations • 4 Mar 2021 • Sara Durrani, Umair Arshad

Finally, we show that performance is improved for low resource language speech affect recognition by achieving the UAR OF 69. 32 and 68. 2 for Urdu and Italian speech affects.

Cross-corpus Transfer Learning