Internship | AI sound recognition and audio quality
Scan&Paint 2D is a tool to visualize stationary sound fields using a single probe solution. The system is suitable for solving many engineering problems, from troubleshooting to acoustic benchmarking. It only takes a few minutes to complete and entire measurement campaign. Results of the scan are translated by the software into a color map, superimposed on a photograph of the measured object.
In this project novel AI tools to automatically detect unwanted acoustic events captured during Scan&Paint measurements should be developed. The work will be focused on identifying signal perturbations such as airflow induced noise, impulsive events or manipulation noise. The proposed signal processing algorithms should automatically detect and classify events as well as quantify the quality of the audio stream. Computer simulations and experimental measurements should be carried out to validate the proposed algorithms and evaluate the limitations of the implemented tools. If the work and findings are of good quality, preparing a publication for an international congress or journal will be encouraged. In summary, the work should include a good description of audio signal processing, computer simulations, test measurements and assessment of experimental results.
The candidate should:
- be proficient programming in MatLab
- be proficient in signal processing
- have prior knowledge in machine learning, audio AI and/or classification techniques