In the last couple of weeks, you have learnt about sequence to sequence models, and you have also been introduced to phonemes, which are the smallest units of speech. In this assignment, you will put these together by implementing a seq2seq model for pronunciation prediction of English words. All the questions and related instructions can be found on this Google Colab link.
Instructions for submission can be found on the notebook. You will turn in a PDF version of the completed notebook on Gradescope. Remember to:
1. Paste the viewable link in the box provided in the notebook.
2. Select pages for the respective questions on Gradescope.
For this assignment, you are required to work independently, i.e., you may not collaborate with other students. You are allowed to discuss general concepts and ideas related to the assignment, but you must not discuss actual solutions. A total of 80 (+10 extra credit) points can be earned in this assignment.
Enroll yourself in the Gradescope class (entry code provided on Piazza) and submit the PDF before 11.59 PM (EDT) on November 5, 2020 (Friday). No late submission is allowed for this assignment. If you face any technical/other difficulties, please contact the TA/CAs on Piazza.
1