Evaluation Metric
The evaluation metric for this competition is frame-level accuracy. There are a total of 223,593 frames in the test set. You will be ranked by unweighted accuracy on those phoneme state labels.
Submission Format
Submission files should contain two columns: Id and Label.

Id: the 0-based index of the frame in the test set [0-223592]

Label: the predicted label of the phoneme [0-137]
Id=0 is the first frame in the first utterance. Id=223,593 is the last frame in the last utterance. A sample submission file is available on the Data page.
Rules
Your model MUST use an MLP (no RNNs or ConvNets). We will check your code to make sure this is the case. However, you are free to use auto-differentiation libraries like PyTorch or Tensorflow.

(Note: Support will most likely only be provided for PyTorch.)