2023
Pre-Trained Model Representations and Their Robustness Against Noise for Speech Emotion Analysis
ICASSP 2023accepted
Pre-trained model representations have demonstrated state-of-the-art performance in speech recognition, natural language processing, and other applications. Speech models, such as Bidirectional Encoder Representations from Transformers (BERT) and Hidden units BERT (HuBERT), have enabled generating l…