An important part of the learning experience associated with this course (and 40% of the grade) comes from experimenting with the algorithms presented in class. This page describes what is expected from the students. Feel free to ask questions below.
The objectives are the following
- get hands-on experience with some of the algorithms presented in the course
- practice the writing of an experimental journal (e.g. on a blog dedicated to your experiments for this course), describing your ideas, experimental plans, experimental results, and discussions of potential conclusions (i.e., the stuff that eventually ends up in papers)
- practice the use of collaborative tools for writing code, using a repository dedicated to your experimental work (e.g., with github)
- practice the collaborative competition typically enjoyed by scientists:
- the work of each student (in the code repository and in the blog) is available to the others to build upon, thus speeding up the overall rate of progress of the group
- each student is encouraged to re-use the ideas, results, tricks, and code from other students but MUST properly cite and acknowledge these inputs (plagiarism without citation would be severely punished)
- each student competes to obtain good results on common benchmarks, but can take advantage of the good ideas of the others, hence the collaborative competition.
- An important part of the grade will come from having been the first to do something useful and publicize it on your blog (possibly posting here announcements with links to the blog). The more this contribution is useful to advancing each other’s progress, the more points will be given. This should provide an incentive to do things quickly that may otherwise look boring but that could be useful to others.
Examples of blogs written by students last year:
For now we will get started by playing with the TIMIT dataset and use it to experiment with the task of speech synthesis, i.e., mapping a sequence of symbols (phonemes or words) to an acoustic sequence (e.g. audio samples). Information about the speaker could also be used (so that eventually we could use such a model to imitate someone’s voice and make him or her say something else than what is available in a recording).
More information about the dataset will soon be added here. For now you can find a page that gives information about the data and previous papers there:
Please start by creating your blog and your code depository, a list of pointers to these will be maintained here:
- Alassane Ndiaye
- Alexis Tremblay
- Amjad Almahairi
- Benjamin Aubert
- David Scott Krueger
- David Belius
- Eric Larsen:
- Jessica Thompson
- João Felipe Santos
- Hubert Banville
- Ishmael Diwan Belghazi
- Jean-Philippe Raymond
- Laurent Dinh
- Marc-André Legault
- Matthieu Courbariaux
- Pierre-Luc Vaudry
- Thomas Rohée
- Vincent Dumoulin
- William Thong