Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment

Benchmark Model Rank Results
emotion-recognition-in-conversation-on-iemocapSPECTRA#41Accuracy: 67.94
multimodal-intent-recognition-on-mintrecSPECTRA#3Accuracy (20 classes): 73.48
multimodal-sentiment-analysis-on-cmu-moseiSPECTRA#3Accuracy: 87.34
multimodal-sentiment-analysis-on-cmu-mosiSPECTRA#9Acc-2: 87.5
multimodal-sentiment-analysis-on-mosiSPECTRA#2Accuracy: 87.50