The SmartLights benchmark from Snipstests the capability of controlling lights in different rooms.
It consists of 1660 requests which are split into five partitions for a 5-fold evaluation.
A sample command could be: “please change the [bedroom] lights to [red]” or “i’d like the [living room] lights to be at [twelve] percent”
Variants: Snips-SmartLights
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Spoken Language Understanding | Finstreder (Quartznet) | Finstreder: Simple and fast Spoken … | 2022-06-29 |
| Spoken Language Understanding | Finstreder (Conformer) | Finstreder: Simple and fast Spoken … | 2022-06-29 |
| Spoken Language Understanding | Finstreder (Conformer, character-based) | Finstreder: Simple and fast Spoken … | 2022-06-29 |
| Spoken Language Understanding | AT-AT | Exploring Transfer Learning For End-to-End … | 2020-12-15 |
| Spoken Language Understanding | Real + synthetic | Using Speech Synthesis to Train … | 2019-10-21 |
| Spoken Language Understanding | Snips | Spoken Language Understanding on the … | 2018-10-30 |
| Spoken Language Understanding | Spoken Language Understanding on the … | 2018-10-30 |
Recent papers with results on this dataset: