The endeavor behind this project was to apply concepts we have learned in EECS 351 to the issue of classifying spoken languages from audio files. As a group, we found that language detection was an interesting project to implement since most of our group members speak or know people who can speak a variety of languages. We aim to use DSP tools in MATLAB and concepts to produce a model that will allow us to classify distinct languages and eventually categorize them into language groups.
The main objective of our project is to create a multi-language identification system that classifies audio recordings from at least three languages with reasonable accuracy (>70%). As a bonus, we would be interested in pushing the limits of the system to see if it can distinguish between similar languages or dialects, and if possible, run our own audio samples to see if it can correctly classify those as well.
Learn about our project by clicking on any section at the top of the screen!
(Background image courtesy of Dreamstime)
[Images © Team 12 unless otherwise stated]