Details
- Supervisors
- Faculty
- Degree label
- Abstract
- Voice assistants are becoming more and more popular. Every platform now tries to have a voice-controlled assistant, and every big company has its assistant, like Alexa, Bixby or google assistant. With the rise of those assistants, users are increasingly accustomed to do basic tasks by voice, and voice recognition frameworks are released frequently. But the moment, there is no easy solution for dictating code. There are only workarounds, solutions that try to allow coding with the voice, but are only tailored for one specific individual, need a big learning curve with strange keywords to control the dictation, and are not easily usable for a lot of users. Since code is so much different from continuous text, we cannot just use classic text recognition and call it a day: we must adapt an existing solution and change it to have a good recognition quality. This thesis will look into this problem; we will see what are the available solutions, what algorithms are used, and see whether they can be used to dictate code by benchmarking their quality in this context.
Citations
Gonze, D. (2020). Coding with the voice. https://dial-mem.test.bib.ucl.ac.be/handle/2078.2/17565