| Approach | Eval 1 | Eval 2 | Eval 3 | Eval 4 |
|---|---|---|---|---|
| Downsampling | 0.081 | 0.245 | ||
| Reference vector | 0.365 | |||
| Correspondence Autoencoder | 0.469 | |||
| Siamese CNN | 0.549 | |||
| Siamese LSTM | 0.671 | 0.559 | ||
| Seq2Seq Autoencoder | 0.262 | |||
| Multi-view embeddings | 0.806 | 0.791 | ||
| Phonetically-associated Siamese network | 0.714 | |||
| Seq2Seq Correspondence Autoencoder | 0.511 | |||
| Multi-view Encoder-Decoder embeddings | 0.879 |
Last active
March 3, 2020 12:20
-
-
Save maobedkova/64add800439401583757baa49f6fa30a to your computer and use it in GitHub Desktop.
AWE approaches - AP scores
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment