NOTE! These pages are deprecated and retained only for archiving purposes. Our new location is https://speechprocessingbook.aalto.fi .



This is a collection of pedagogical material within the topic of speech and language technology. The idea is to provide

  • teachers material for their courses, where they can pick and choose material which is appropriate for their own courses.
  • self-study material on-line for anyone interested.

By licensing the material under creative commons (share alike), we want to encourage people to contribute improvements and additions to the content.


Edit-access will be granted by mailto:tom.backstrom@aalto.fi


Design philosophy of this document

  • Target audience
    • Primary target:
      • Master's level students with some background in digital signal processing (=signals and systems), machine learning, linear algebra and stochastic processes
    • Secondary targets:
      • Researchers in related areas who want to expand their expertise, for example, researchers in machine learning, signal processing, audio processing, linguistics, human-computer interfaces etc
  • Keep a pedagogical approach
    • Explain why this tool is needed and how it solves a problem.
    • Give an example of how it is used in practice, including demonstrations and pictures.
    • Favour tools which everyone are using, rather than inventions of your own team
  • Small steps
    • Better to have something than nothing. Though it is a good direction, reaching perfection is not a requirement.
    • Fix errors immediately when you find one.


  • No labels