MSP-Podcast
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Speech Emotion Recognition | MSP-Podcast | UA66.4 | 22 | |
| Automatic Speech Recognition | MSP-Podcast (Test2) | WER0.1442 | 13 | |
| Automatic Speech Recognition | MSP-Podcast (Test1) | WER15.6 | 13 | |
| Speech Emotion Recognition | MSP-Podcast (test1) | P-MacroF142.24 | 10 | |
| Speech Emotion Recognition | MSP-Podcast 2.0 (test 3) | WAR42.12 | 8 | |
| Empathetic Response Generation | MSP-PODCAST | Emotional Reaction Score1.889 | 8 | |
| Speech Emotion Recognition | MSP-Podcast 2.0 (test) | Weighted Accuracy (WAR)60.58 | 5 | |
| Speech Emotion Recognition | MSP-Podcast 2.0 (test 1) | Weighted Accuracy Rate (WAR)62.39 | 5 | |
| Acoustic Emotion Recognition | MSP-Podcast 1.6 (test) | Valence (v)0.629 | 4 | |
| Speech Emotion Recognition | MSP-Podcast | WER0 | 3 | |
| Emotion Recognition | MSP-Podcast | JS Divergence0.33 | 3 | |
| Acoustic Emotion Recognition | MSP-Podcast 1.8 (test) | Valence Score (v)0.506 | 2 | |
| Speech Emotion Recognition | MSP-Podcast (test) | Metric- | 0 |
Showing 13 of 13 rows