About the project

This is a collaboration between researchers in linguistics, mathematics and statistical physics from Cambridge and Portsmouth Universities.

We developed a web-app that records a short sample of your speech, detects the vowels in that recording, and then classifies the vowels and displays them on a vowel chart. On this vowel chart you will be able to compare the positions of your vowels to those of a generic Southern English dialect.

We have been funded by the University of Cambridge Language Sciences Incubator Fund (LINK).

Creators and Contributors

Michal Gnacik James Burridge Bert Vaux

Michal is a Senior Lecturer in the School of Mathematics and Physics at the University of Portsmouth. Michal wrote the web-app code and further developed and trained the neural networks used within the extraction and visualization models.
James is a Reader in Probability and Statistical Physics in the School of Mathematics and Physics at the University of Portsmouth. James devised the project and developed the vowel extraction and visualization models used in the app.
Bert is a Professor of Phonology and Morphology in the Faculty of Modern & Medieval Languages & Linguistics at the University of Cambridge. He provided guidance on the linguistic components of the project and contributed to the vowel chart framework.
Jascha Schewtschenko Krystian Łapa

Jascha is a Research Data and Software Specialist in the Institute of Cosmology and Gravitation at the University of Portsmouth. Jascha has been helping us improve the code structure of the app.
Krystian is a Professor at the Częstochowa University of Technology in Poland. Krystian has helped us with the modification of the Java-Script Audio Recorder.

Quick Access