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
- Primary target:
- 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.
Licence
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.