Spoken Language Understanding On Snips
Metrics
Accuracy (%)
Results
Performance results of various models on this benchmark
Model Name | Accuracy (%) | Paper Title | Repository |
|---|---|---|---|
| 79.3 | Spoken Language Understanding on the Edge | ||
| Snips | 84.2 | Spoken Language Understanding on the Edge | |
| Real + synthetic | 71.4 | Using Speech Synthesis to Train End-to-End Spoken Language Understanding Models | |
| AT-AT | 84.9 | Exploring Transfer Learning For End-to-End Spoken Language Understanding | - |
| Finstreder (Conformer, character-based) | 89.0 | Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models | |
| Finstreder (Conformer) | 88.0 | Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models | |
| Finstreder (Quartznet) | 84.8 | Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models |
0 of 7 row(s) selected.