Roadmap
Here's an attempt at roadmap for Merlin.
At some point, we might extend the stuff on speech.zone to be more general.
In the meantime, if you are coming to Interspeech 2017, then please come to our tutorial!
Can be mostly handled by describing how to modify an existing recipe
Will need to wait for Ossian to go on to GitHub, then add recipes to that, not Merlin.
Add the 2016 benchmark system recipe. Need to change the dictionary to something Open Source, instead of Combilex.
2017 benchmark should use more sophisticated architecture - perhaps (simplified) LSTM and/or stacked bottleneck features.
RELU units
Convolutional layers
Visualise t-SNE embeddings of hidden layer activations during training
Web interface to monitor training (extend the logger / plotter stuff)
