You are here:Home Practical exercises

Practical exercises

Here you will find some practical exercises to help you understand the material in the courses.

  • Familiarisation

    In these simple exercises, we get our hands on speech and other audio signals, and analyse them in various ways. We use the Wavesurfer and Praat tools.

  • The Festival text-to-speech system

    Festival is a widely used research toolkit for Text-To-Speech. It is not perfect, and your goal is to discover various types of errors it makes, then understand why they occur.

  • Build your own digit recogniser

    A simple but functional digit recogniser built from scratch: record and label data, train HMMs, create a language model, and recognise the test data. Extend to other speakers & digit sequences.

  • Build your own neural speech synthesiser

    This exercise is the replacement for building your own unit selection voice. You will use your data to train a neural sequence-to-sequence model, similar to FastSpeech 2.

  • Dynamic Time Warping (DTW) in Python

    Dynamic Time Warping (DTW) is a nice introduction to the key concept of Dynamic Programming.

  • Build your own unit selection voice

    Record your speech and build a unit selection voice for Festival. Create variations of the voice, add domain specific data, or vary the database size. Evaluate with a listening test.

  • Build your own DNN voice using the Merlin toolkit

    This exercise assumes that you have already built your own unit selection voice, and therefore have all the data you need.

  • Signal Processing Courses in Crete

    Special versions of the unit selection and DNN exercises for this summer school

  • Mini literature review

    Just because research is published, doesn't mean it is perfect! That's the theme of this miniature literature review.