In the last couple of weeks, you have learned about the classic and end-to-end paradigms of speech recognition. In this assignment, you will build an end-to-end ASR for a subset of Librispeech, using the CTC framework that you learned in class. 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 110 (+15 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 30, 2020 (Monday). No late submission is allowed for this assignment. If you face any technical/other difficulties, please contact the TA/CAs on Piazza.
1