Implementation Tips
Network Architecture
*Your MUST use MLP (e.g. no RNN or CNN)*

Feel free to experiment with different architectures. The simplest approach is to build a feedforward network that takes in a single frame (input size 40) and outputs probabilities across phoneme states using a softmax output to normalize the logits.

(Hint1: Rolling in the deep.)

(Hint2: What have you learned from part 1?)
Context
Temporal context is important for distinguishing elements of speech and you can experiment with adding context to your ANN model. For example, you can try concatenating k mel spectrogram frames around the current time step. This technique would make the size of the input vector 40 * (2k + 1). You will need to adjust your data preprocessing and batching logic to adapt for frame context. Writing code that will let you experiment with variable context sizes easily is recommended.

Intuition: Since each mel spectrogram frame is only 25ms of the speech audio data, a single frame is unlikely to represent a complete phoneme. Concatenating nearby "k" frames will thus be helpful. Here "k" can be viewed as a hyperparameter for you to try out.

(Hint: This is the key to boost your score!)
Data Batching
It is important to consider that the data is provided in the form of utterance samples and not frame samples. The property of mini-batch SGD that gradients over all batches in an epoch approximate the true gradient only holds if each batch is IID (Independent and Identically Distributed). If we sample uniformly over utterances and also sample uniformly over frames within the utterance, our batches will surely not be IID. For example, different utterances will have considerably different numbers of phoneme instances. Sampling uniformly biases the training data by over-representing phonemes in the utterance with fewer phonemes (and therefore its phoneme states). You can try a different sampling technique to batch your training data to mitigate this issue.

Many approaches are possible. See what can get you to the top of the leaderboard!