Report Write-up

Sections 1-5: Error Analyses

For the each of the error analysis sections (1-5), you should at least:

• Clearly describe exactly the error you have found. That is, tell us:
  • What the text input to Festival was
  • What the expected (i.e., correct) output should have been
  • What the actual output was
• Clearly explain what TTS pipeline component is responsible for the error and why the error happened in that component. Provide evidence to support your explanation.

Try to be precise in pointing out how the error appears in the linguistic specification and/or the generated waveform (as appropriate). You may find it useful (in some cases necessary) to use tables or figures to illustrate the errors or explanations of where they came from.

Beyond this, you can get more marks for showing more depth of analysis, for example:

• Further analysis/more evidence of mistakes’ origins, e.g. if it’s due to interactions of modules
• Analysis of severity of mistakes, e.g., Would it affect output frequently or only rarely?
• Further analysis of the error from a phonetics perspective, e.g., why does it sound bad? Why might the error affect speech intelligibility or naturalness? Is the error something a human speaker might also make?
• Discussion of potential solutions
• Use of citations to further support your claims/argument
• Other relevant insights into the errors, especially those that highlight differences between theory and practice.
• Use of figures, tables, other visualizations to make your answer more informative. It will be much easier to report some types of errors with tables, but some will require figures (e.g., waveform errors).

You can describe more than one error per category, but note that you’ll likely get more marks for showing more depth of understanding about the category as a whole. So, several very similar examples will probably not get you as much as an in-depth analysis of a specific example that really shows that you understand what that particular part of the TTS pipeline does (and potentially how it interacts with other parts of the TTS process).

Section 6: TTS pipeline discussion

In the TTS pipeline discussion section, you should discuss the overall implications of your error analysis. When formulating your answer, consider the questions raised in the task description.

When writing up your discussion, imagine that you are a consultant and have been asked to provide recommendations to the company that produced this voice. They have a limited budget and limited time to spend on improving the voice. What should they focus their attention on to improve the voice? What are the most important problems to fix? What are the potential tradeoffs between the usefulness or generalisability of potential solutions, and the effort that would be needed to implement those solutions?

Assume here that the company is committed to sticking with a unit selection voice, so focus on recommendations regarding this voice (i.e., don’t just say change to use a neural network based approach!)

You can consider errors that you found that you didn’t write up in the first part of the report here. However, if you do introduce new error examples in this discussion, you will need to explain them clearly.

Bibliography

You should provide references for any claims you make outside of what has been covered in the essential course materials. It is not necessary to cite course lectures or videos, though you may wish to reference the readings and other related works.

You can gain extra marks for bringing in insights from related work to strengthen your argumentation (i.e., academic papers that are not on the essential reading list). However, you should be able to complete this assignment to a good standard working just with the core course materials.